{ "metrics": { "bleu": 1.779488646466125, "bleu_signature": "nrefs:1|case:mixed|eff:no|tok:13a|smooth:exp|version:2.6.0", "chrf": 21.42976562133535, "chrf_signature": "nrefs:1|case:mixed|eff:yes|nc:6|nw:2|space:no|version:2.6.0", "exact_match": 0.0, "empty_outputs": 0, "source_copy_outputs": 0, "mean_prediction_characters": 31.995956873315365, "mean_reference_characters": 36.26145552560647, "rows": 742, "num_beams": 4, "no_repeat_ngram_size": 3, "repetition_penalty": 1.1, "length_penalty": 1.0 }, "predictions": [ { "id": "mic-sent-0041f567c40884651287c94e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is looking for his/her shirt, he/she doesn't know he/she is wearing it.", "output_text": "Algwiluatl ugatlaiml, mu geitug alnasguatl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is looking for his/her shirt, he/she doesn't know he/she is wearing it.", "mic_Latn": "Algwiluatl ugatlaiml, mu geitug alnasguatl." }, "canonical_ref": "entries/a/algwiluatl/algwiluatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3623ec0be69261d9f6e4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/algwiluatl/algwiluatl.html", "entry_url": "https://mikmaqonline.org/entries/a/algwiluatl/algwiluatl.html", "headword": "algwiluatl", "example_index": 0, "raw_html_path": "raw/entries/01f5f2890013fe746753d0d8a6c849e5f284eaf7bbf9b68dbcea90cd41d3d618.html", "raw_html_sha256": "0889f589641c449b90a6bf93a2d89991f54cd0ad4db02a6b4593e752c8245e9f", "fetched_at": "2026-07-12T02:36:39.927Z", "recordings": [ { "recording_id": "6ea416c278911781397349795743fbe27db57250d27d5874d8b45df17d4f6b37", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/68a/68ab9ddf06172ba01efe14d67b2b271c2ac0795d48a271766046716cfe1242c4.mp3", "archive_relative_path": "raw/audio/68a/68ab9ddf06172ba01efe14d67b2b271c2ac0795d48a271766046716cfe1242c4.mp3" } ] } ], "prediction": "Gesatg ugta'latl, mu ge's goqwei e'watl.", "reference": "Algwiluatl ugatlaiml, mu geitug alnasguatl." }, { "id": "mic-sent-0043080fb724f54b5882ab84:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Everyone bows to the alter in church.", "output_text": "Ms't wen matgwetoq patgulme'sigaqan a's'tuo'guomg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Everyone bows to the alter in church.", "mic_Latn": "Ms't wen matgwetoq patgulme'sigaqan a's'tuo'guomg." }, "canonical_ref": "entries/m/matgwetoq/matgwetoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2aad70203c4afcbbb63a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/matgwetoq/matgwetoq.html", "entry_url": "https://mikmaqonline.org/entries/m/matgwetoq/matgwetoq.html", "headword": "matgwetoq", "example_index": 0, "raw_html_path": "raw/entries/948484a901185ec8f34640e4b98a8ece7902adffae42baa756b7610532ae90c1.html", "raw_html_sha256": "1de7206daa80122da2f9734f8f758ee9615d6a4f5baae7beeabddd6418caaea8", "fetched_at": "2026-07-12T02:40:54.664Z", "recordings": [ { "recording_id": "933276d0f44aa580449846662ba1f029e57b805c79d87ccf11065d2f04f85109", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/94c/94cb253040004174c0fb21adc37c1017470439c7357354fe8c547cf530eeed55.mp3", "archive_relative_path": "raw/audio/94c/94cb253040004174c0fb21adc37c1017470439c7357354fe8c547cf530eeed55.mp3" } ] } ], "prediction": "Ms't wen gi's gesgm'g na alpaqanigtug.", "reference": "Ms't wen matgwetoq patgulme'sigaqan a's'tuo'guomg." }, { "id": "mic-sent-004d43f45782c1f00b4a5493:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Even when he/she tries not to be, sometimes one is envious.", "output_text": "Tlia' ugjo'tg mu tla'tegn, gijuaqa na wen wisguet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Even when he/she tries not to be, sometimes one is envious.", "mic_Latn": "Tlia' ugjo'tg mu tla'tegn, gijuaqa na wen wisguet." }, "canonical_ref": "entries/w/wisguet/wisguet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-38ae921f4e22c83e2a5f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wisguet/wisguet.html", "entry_url": "https://mikmaqonline.org/entries/w/wisguet/wisguet.html", "headword": "wisguet", "example_index": 0, "raw_html_path": "raw/entries/bd185a7b5e2894b21767a77fbfc4149a3864417fa7873e737045d419817efd4d.html", "raw_html_sha256": "9cfdf72bf66d9d3da39e80d6ae59a0808c7ad259a33ad4478cd727a651f14c8a", "fetched_at": "2026-07-12T02:47:38.767Z", "recordings": [ { "recording_id": "e6e8818da1ec627d9cbe81d6c0094528156674198efa917d15d2e9d9335cba76", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/133/1334193735a6468578d5fbfec74f93316de4d10cb172ab229717fc48d0b1c37a.mp3", "archive_relative_path": "raw/audio/133/1334193735a6468578d5fbfec74f93316de4d10cb172ab229717fc48d0b1c37a.mp3" } ] } ], "prediction": "Gi's ta'n tujiw nugu' negm, te's na ji'nm.", "reference": "Tlia' ugjo'tg mu tla'tegn, gijuaqa na wen wisguet." }, { "id": "mic-sent-0074fe077d48ff5db95b6c81:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she wraps the meat in a layer of fat and cooks it slowly.", "output_text": "Oqonisqopilg wius wigewigtug aq sangew etloqs'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she wraps the meat in a layer of fat and cooks it slowly.", "mic_Latn": "Oqonisqopilg wius wigewigtug aq sangew etloqs'g." }, "canonical_ref": "entries/o/oqonisqopilg/oqonisqopilg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bc104a3e97dd084d37af", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/o/oqonisqopilg/oqonisqopilg.html", "entry_url": "https://mikmaqonline.org/entries/o/oqonisqopilg/oqonisqopilg.html", "headword": "oqonisqopilg", "example_index": 0, "raw_html_path": "raw/entries/680a256d100ed68ff207220797c23d6218652ab0354698569fe9f7777fdd8d87.html", "raw_html_sha256": "b2a2db8ecf4cc1badd91ce1b1f4b2d258c5f494ed869e76465859a9f079f9a87", "fetched_at": "2026-07-12T02:43:01.453Z", "recordings": [ { "recording_id": "fc9ee766f790f5cd28261680eff3531d223fec262fe007af4078bdbcbcf6e39b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e73/e73f5fc549d49d87313add8d580d2171e09afe5d709aaefbe2bde37223a5b008.mp3", "archive_relative_path": "raw/audio/e73/e73f5fc549d49d87313add8d580d2171e09afe5d709aaefbe2bde37223a5b008.mp3" } ] } ], "prediction": "Pugwelga'latl na wi'gatl aq gesgm't.", "reference": "Oqonisqopilg wius wigewigtug aq sangew etloqs'g." }, { "id": "mic-sent-00b4fba8540c29072eb7b6fd:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Can you please show me how your house will be built?", "output_text": "Ge' neia'tui ta'n tliganitew gi'g?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Can you please show me how your house will be built?", "mic_Latn": "Ge' neia'tui ta'n tliganitew gi'g?" }, "canonical_ref": "entries/t/teliganig/teliganig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-768f5aa76126bb315dbc", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/teliganig/teliganig.html", "entry_url": "https://mikmaqonline.org/entries/t/teliganig/teliganig.html", "headword": "teliganig", "example_index": 0, "raw_html_path": "raw/entries/8a99fb2e41a1b04015511d9d9da4a3e6c28560a1f66492981340aa08462b8b87.html", "raw_html_sha256": "8611bc6ac0ac1a689b3b415b57614cb2f99627ddca747bb7e9a687d6ab19e1b9", "fetched_at": "2026-07-12T02:36:11.266Z", "recordings": [ { "recording_id": "e8d3b447cfe3b5f75e9fc06027f24e6f7010e0703f1e078ef7add5c00a9710c1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a9f/a9fe437c3ab354e4edf3ca96cf867573f22a4f954f3d142156f4f146fb247802.mp3", "archive_relative_path": "raw/audio/a9f/a9fe437c3ab354e4edf3ca96cf867573f22a4f954f3d142156f4f146fb247802.mp3" } ] } ], "prediction": "Ge' ge' jugwa'tu ta'n tujiw muta wejiaq?", "reference": "Ge' neia'tui ta'n tliganitew gi'g?" }, { "id": "mic-sent-011d3db509d024649bdbaf77:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The sugar bowl is empty, where can I find more?", "output_text": "Sigue'g ula sismo'qono'q, tami me' we'jites?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The sugar bowl is empty, where can I find more?", "mic_Latn": "Sigue'g ula sismo'qono'q, tami me' we'jites?" }, "canonical_ref": "entries/s/sismo'qono'q/sismo'qono'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-96c9a68457ea72583fd3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sismo'qono'q/sismo'qono'q.html", "entry_url": "https://mikmaqonline.org/entries/s/sismo'qono'q/sismo'qono'q.html", "headword": "sismo'qono'q", "example_index": 0, "raw_html_path": "raw/entries/7f907b19b1ff500a3e2e1ce9436d98c3b180e8759ea875e37b432d964c4c0d6f.html", "raw_html_sha256": "78fddb0a1f60d4397d9786b58ba44155206bde7e7c1d36009538493ed74c28ab", "fetched_at": "2026-07-12T02:45:08.981Z", "recordings": [ { "recording_id": "a3c4cdaadf58e761b09463fce23c940927ba445f64181a537cd3765078e42699", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/662/6624fbccfc49acbd5b2dc22a88f44f21aa2c964ba543814beec08a02f5e22005.mp3", "archive_relative_path": "raw/audio/662/6624fbccfc49acbd5b2dc22a88f44f21aa2c964ba543814beec08a02f5e22005.mp3" } ] } ], "prediction": "Pugwelg'g ugjit, ta'n goqwei newte'l?", "reference": "Sigue'g ula sismo'qono'q, tami me' we'jites?" }, { "id": "mic-sent-014dccf2e64b7258362484c8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The boy gets a hold of his dog and takes it home.", "output_text": "L'patuj gisapsgnatl ugti'l aq enma'latl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The boy gets a hold of his dog and takes it home.", "mic_Latn": "L'patuj gisapsgnatl ugti'l aq enma'latl." }, "canonical_ref": "entries/g/gisapsgnatl/gisapsgnatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a5719de27b2335d0104f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gisapsgnatl/gisapsgnatl.html", "entry_url": "https://mikmaqonline.org/entries/g/gisapsgnatl/gisapsgnatl.html", "headword": "gisapsgnatl", "example_index": 0, "raw_html_path": "raw/entries/bec96c656e6b59f1abca64968b12160db5928c81c767fa7fea8650c9a0639aa6.html", "raw_html_sha256": "cd6092e270d2e0159ffc51242a7ac37c7dfe45ed08b6e8582b58e96cc96a96cc", "fetched_at": "2026-07-12T02:39:36.050Z", "recordings": [ { "recording_id": "1733bcb8c323a9a3b980fbecd2a3ce0fffe372b647a38cca0844ae86dab8c324", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d3c/d3cf55fafdd08b514ed994370a9e94989b88d9a6fc5364941e005931cf35d986.mp3", "archive_relative_path": "raw/audio/d3c/d3cf55fafdd08b514ed994370a9e94989b88d9a6fc5364941e005931cf35d986.mp3" } ] } ], "prediction": "Lpa'tu'ji'j gesatg ugti'l aq e'watl.", "reference": "L'patuj gisapsgnatl ugti'l aq enma'latl." }, { "id": "mic-sent-01f565a30ba9c14ce97f892c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My aunt lives in a spruce bark covered house.", "output_text": "Nsugwis pqawi'ganmit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My aunt lives in a spruce bark covered house.", "mic_Latn": "Nsugwis pqawi'ganmit." }, "canonical_ref": "entries/p/pqawi'ganmit/pqawi'ganmit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-46bbae56c8d67923fab7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pqawi'ganmit/pqawi'ganmit.html", "entry_url": "https://mikmaqonline.org/entries/p/pqawi'ganmit/pqawi'ganmit.html", "headword": "pqawi'ganmit", "example_index": 0, "raw_html_path": "raw/entries/945f35749be4a8016f8d16bef30df584082b7bfdedfb52ae7b6427c5d567fa88.html", "raw_html_sha256": "860742d4fc02b78ba376a24f66609d50d21e3f751935bb263d36115a16cf65c3", "fetched_at": "2026-07-12T02:36:29.272Z", "recordings": [ { "recording_id": "2df1f0c2828e228b71cc72eec67909a5eb6ed0816a09c76036d2b361ba4feebb", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0a9/0a9fc56fba3e9a8209d8805ae0f12acb3f6e26577452c547c232b85849d0616c.mp3", "archive_relative_path": "raw/audio/0a9/0a9fc56fba3e9a8209d8805ae0f12acb3f6e26577452c547c232b85849d0616c.mp3" } ] } ], "prediction": "Ntlugowa'q ugjit gmu'ji'j.", "reference": "Nsugwis pqawi'ganmit." }, { "id": "mic-sent-02b144bd23414474c1f1d4b8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "How about you, are you ticklish?", "output_text": "Gatu gi'l, gi'gligsin?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "How about you, are you ticklish?", "mic_Latn": "Gatu gi'l, gi'gligsin?" }, "canonical_ref": "entries/g/gi'gligsit/gi'gligsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-850c4847ea4021a4e1c4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gi'gligsit/gi'gligsit.html", "entry_url": "https://mikmaqonline.org/entries/g/gi'gligsit/gi'gligsit.html", "headword": "gi'gligsit", "example_index": 0, "raw_html_path": "raw/entries/324f1cb4353ee14f7724fef95a9bd34fb2fa7b02472e7e3b993f779a267cf570.html", "raw_html_sha256": "458c971e8f13973b272afcb945bd172b7a5ec3c6314193cb534f33bccf7aaded", "fetched_at": "2026-07-12T02:39:30.425Z", "recordings": [ { "recording_id": "f812afee0d87bf0fddc5eaff5f5cd12aeaed745951d454db2dc5dc004983792b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/897/897a21b12448453d36cf6322f927715023b647e174a3ec987d030c65d1c6b72b.mp3", "archive_relative_path": "raw/audio/897/897a21b12448453d36cf6322f927715023b647e174a3ec987d030c65d1c6b72b.mp3" } ] } ], "prediction": "Goqwei etug, lpa gmu'ji'j?", "reference": "Gatu gi'l, gi'gligsin?" }, { "id": "mic-sent-02c4bee500ef5565c30337c2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I saw him\\her down the shore a while ago towing his\\her boat along.", "output_text": "Gejigow nemi'g'pnaq sitmug pempilg ugtul.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I saw him\\her down the shore a while ago towing his\\her boat along.", "mic_Latn": "Gejigow nemi'g'pnaq sitmug pempilg ugtul." }, "canonical_ref": "entries/p/pempilg/pempilg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0a467f51b436069f4f26", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pempilg/pempilg.html", "entry_url": "https://mikmaqonline.org/entries/p/pempilg/pempilg.html", "headword": "pempilg", "example_index": 0, "raw_html_path": "raw/entries/7915784c3b37578b3bfb08f1903765891a99fd64d7d23923e2c3bd43943adaba.html", "raw_html_sha256": "7e21dc513a702d727710d6293a13e2751fabdab5e0b20038d32cd864107daa2a", "fetched_at": "2026-07-12T02:43:35.937Z", "recordings": [ { "recording_id": "bbd82ab54d4292aca221dc754e931c062d654539f9ed83e474f752cc91818d2a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0da/0da6cda19331b3bace8d0fc40d22317497f0c5935ee31d1a9183fbe671242c8d.mp3", "archive_relative_path": "raw/audio/0da/0da6cda19331b3bace8d0fc40d22317497f0c5935ee31d1a9183fbe671242c8d.mp3" } ] } ], "prediction": "Gi's gi'l nemi'tmu'j gesgmnaq ugjit ugjit.", "reference": "Gejigow nemi'g'pnaq sitmug pempilg ugtul." }, { "id": "mic-sent-030bd1abe31d809d1ded1317:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Today I'm going to see the doctor (who is female).", "output_text": "Gisgug malpale'wi'sgw natnmi'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Today I'm going to see the doctor (who is female).", "mic_Latn": "Gisgug malpale'wi'sgw natnmi'g." }, "canonical_ref": "entries/m/malpale'wi'sgw/malpale'wi'sgw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2a526243a5b53c0a4810", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/malpale'wi'sgw/malpale'wi'sgw.html", "entry_url": "https://mikmaqonline.org/entries/m/malpale'wi'sgw/malpale'wi'sgw.html", "headword": "malpale'wi'sgw", "example_index": 0, "raw_html_path": "raw/entries/42e9791e6e19b1ca66e17cb0e8949729912569af16fbd4dcddf7a08912232413.html", "raw_html_sha256": "3e17fc308ace2a40ad5d55496a2f2511ac6c9588397bbd6aeebd54a0f55401df", "fetched_at": "2026-07-12T02:40:45.436Z", "recordings": [ { "recording_id": "94ebf994764e841a9098e64419b6622ef354d36e59f0641f8b8935a4cc57a501", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/284/2843b22a3d770e68a13ffbd24d62c93984233d94412401f75b68a4d1ea713188.mp3", "archive_relative_path": "raw/audio/284/2843b22a3d770e68a13ffbd24d62c93984233d94412401f75b68a4d1ea713188.mp3" } ] } ], "prediction": "Gisgug gi's ni'n goqwei lpa lpa'toq.", "reference": "Gisgug malpale'wi'sgw natnmi'g." }, { "id": "mic-sent-036ffaf4204538ea49a48f17:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Joseph and Mary are pounding the white ash into splints.", "output_text": "So'sep aq Mali'j eligpete'gejig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Joseph and Mary are pounding the white ash into splints.", "mic_Latn": "So'sep aq Mali'j eligpete'gejig." }, "canonical_ref": "entries/e/eligpete'get/eligpete'get.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-853211e87f9bfa46091e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/eligpete'get/eligpete'get.html", "entry_url": "https://mikmaqonline.org/entries/e/eligpete'get/eligpete'get.html", "headword": "eligpete'get", "example_index": 0, "raw_html_path": "raw/entries/e2fa919da53c59cb5d84a9f4e1728d036518c17e2d6aa63f96066a8edd990e88.html", "raw_html_sha256": "83770f3059b7ffdc7ae5dc31a12717aeffc489296342e15bb51384edfa0a2463", "fetched_at": "2026-07-12T02:37:44.801Z", "recordings": [ { "recording_id": "1f26f445b8ed264d54663a1f4a00ec2861e4a233255e3a3cdd26dec83a444ba9", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ccd/ccd0fd4782727854436f9cdb50fe6f43a7dc56dbc9436541130f46049092b3db.mp3", "archive_relative_path": "raw/audio/ccd/ccd0fd4782727854436f9cdb50fe6f43a7dc56dbc9436541130f46049092b3db.mp3" } ] } ], "prediction": "So'sep aq Mali na'te's'g'p't'p ala'toq.", "reference": "So'sep aq Mali'j eligpete'gejig." }, { "id": "mic-sent-03e80561852a345b545f7507:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I drive everything home today.", "output_text": "Ms't goqwei enmateja'tu gisgug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I drive everything home today.", "mic_Latn": "Ms't goqwei enmateja'tu gisgug." }, "canonical_ref": "entries/e/enmateja'toq/enmateja'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3dd642722ebdea8e0ff5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/enmateja'toq/enmateja'toq.html", "entry_url": "https://mikmaqonline.org/entries/e/enmateja'toq/enmateja'toq.html", "headword": "enmateja'toq", "example_index": 0, "raw_html_path": "raw/entries/55bdcb07281381272636aceaebb6e177d093d559b57590041f4932dbf5d0b3e8.html", "raw_html_sha256": "b1289474f92c6b16eb072f29396cc983941fdbe0eb370e09d838b28b0b99f362", "fetched_at": "2026-07-12T02:38:00.979Z", "recordings": [ { "recording_id": "c14b5ea33659d94925eda2761817a44fc352a58326940a6a777d2f7dbec0a9cf", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/27b/27bb98172e4d928d04a3035774f666948e9b166784f8d1aa70708bc8a4614278.mp3", "archive_relative_path": "raw/audio/27b/27bb98172e4d928d04a3035774f666948e9b166784f8d1aa70708bc8a4614278.mp3" } ] } ], "prediction": "Gisgug ms't goqwei gisgug.", "reference": "Ms't goqwei enmateja'tu gisgug." }, { "id": "mic-sent-04842a8501d780c319a27374:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Joseph used to like to smoke.", "output_text": "So'sep pusgigsatg'p wetmatj.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Joseph used to like to smoke.", "mic_Latn": "So'sep pusgigsatg'p wetmatj." }, "canonical_ref": "entries/p/pusgigsatg'p/pusgigsatg'p.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-897bef583891b21113d6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pusgigsatg'p/pusgigsatg'p.html", "entry_url": "https://mikmaqonline.org/entries/p/pusgigsatg'p/pusgigsatg'p.html", "headword": "pusgigsatg'p", "example_index": 0, "raw_html_path": "raw/entries/bc60b6eb4f34d0840bec972875180c5ec1edb6c853b1b0dbeca179c25da0f25c.html", "raw_html_sha256": "a8f033c165154d452a2fd72ae3743751100b671930886c2189011d9c2766532e", "fetched_at": "2026-07-12T02:44:28.389Z", "recordings": [ { "recording_id": "88e93df9f31081cd9c9099cade43234e0d10c25f9010c81d255fdfb219db6a1f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2c9/2c928fb80640a5d96620be11abe12acc9aecc0e633fb5cb7bdd3f9532126cb39.mp3", "archive_relative_path": "raw/audio/2c9/2c928fb80640a5d96620be11abe12acc9aecc0e633fb5cb7bdd3f9532126cb39.mp3" } ] } ], "prediction": "So'sep gesatg na'te'g.", "reference": "So'sep pusgigsatg'p wetmatj." }, { "id": "mic-sent-04f7325e725840cfd3f7d603:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she runs out into the open and (then) runs into hiding.", "output_text": "Musgi'pit aq aqui'pit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she runs out into the open and (then) runs into hiding.", "mic_Latn": "Musgi'pit aq aqui'pit." }, "canonical_ref": "entries/m/musgi'pit/musgi'pit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c15d80a18bd42b26b4c9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/musgi'pit/musgi'pit.html", "entry_url": "https://mikmaqonline.org/entries/m/musgi'pit/musgi'pit.html", "headword": "musgi'pit", "example_index": 0, "raw_html_path": "raw/entries/93b14da4e3dfb6a74e809a754bd4669d6d65ce414bd2ab549ad14f008d0e908f.html", "raw_html_sha256": "8d1abbb087ddad379f27e21a949f40b890399ba0bd315b8bb9b949d35f4a2853", "fetched_at": "2026-07-12T02:41:50.454Z", "recordings": [ { "recording_id": "dabb040fc4e512316adde1bb0b09e65c6bd7d1875585310f060f874cedb2d884", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/aaf/aaf3f37838db7b65557fe4207396dad053da4ec8145287a090c4a7e25676afb4.mp3", "archive_relative_path": "raw/audio/aaf/aaf3f37838db7b65557fe4207396dad053da4ec8145287a090c4a7e25676afb4.mp3" } ] } ], "prediction": "Pugwelga'latl aq gesatg.", "reference": "Musgi'pit aq aqui'pit." }, { "id": "mic-sent-04fe3a7e9bf38091db957f9e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I sweeten (it) when I have tea.", "output_text": "Sewa'tai ta'n tujiw p'te'w'mai.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I sweeten (it) when I have tea.", "mic_Latn": "Sewa'tai ta'n tujiw p'te'w'mai." }, "canonical_ref": "entries/s/sewa'tat/sewa'tat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ea9040b81d8b5864ed5c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sewa'tat/sewa'tat.html", "entry_url": "https://mikmaqonline.org/entries/s/sewa'tat/sewa'tat.html", "headword": "sewa'tat", "example_index": 0, "raw_html_path": "raw/entries/1507575af5946375e53d0109344305520bf02264d51da746cb36a4556da4148d.html", "raw_html_sha256": "2e4fcde4880a0dd96cb310680c713e51ec8fdc456832193db221878f6f78d822", "fetched_at": "2026-07-12T02:44:55.511Z", "recordings": [ { "recording_id": "6c8d71d81919e1cbfe53bc42df0ade9456cdae76a065a2955c51fbed2f076cbd", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b57/b57ddbca80067145aa29d4a1d8e41899281159fa3013d61bbb5d88001b999ed2.mp3", "archive_relative_path": "raw/audio/b57/b57ddbca80067145aa29d4a1d8e41899281159fa3013d61bbb5d88001b999ed2.mp3" } ] } ], "prediction": "Pugwelg ta'n tujiw te's.", "reference": "Sewa'tai ta'n tujiw p'te'w'mai." }, { "id": "mic-sent-054205978e1210a997cd0962:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It is strong enough to hold two thousand pounds.", "output_text": "Tepignaq ula gnnmn tapu'gl pituimtnaqanl ngatignn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It is strong enough to hold two thousand pounds.", "mic_Latn": "Tepignaq ula gnnmn tapu'gl pituimtnaqanl ngatignn." }, "canonical_ref": "entries/t/tepignaq/tepignaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7af0a4a906b1ad58a18d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tepignaq/tepignaq.html", "entry_url": "https://mikmaqonline.org/entries/t/tepignaq/tepignaq.html", "headword": "tepignaq", "example_index": 0, "raw_html_path": "raw/entries/5ac3b8b1f9ecefad5a5ee1b2df194b0a820d48a0b17ec0adba85f8bbc3c74642.html", "raw_html_sha256": "c21b1975b7e64f0eacbbcfb97d7a0b896bd9b69eb28babdcf93b53787333e9fd", "fetched_at": "2026-07-12T02:45:42.659Z", "recordings": [ { "recording_id": "c79041861ca1d054ba692ceddfcbe0460651717eb95b53ce14cc45eda69c6f84", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a82/a820c81e9ec6abf0d967a89394f57a2590493541ee0a8053819337df5e1f22ce.mp3", "archive_relative_path": "raw/audio/a82/a820c81e9ec6abf0d967a89394f57a2590493541ee0a8053819337df5e1f22ce.mp3" } ] } ], "prediction": "Te's gesatg ta'n tujiw te's'pg na'te'g.", "reference": "Tepignaq ula gnnmn tapu'gl pituimtnaqanl ngatignn." }, { "id": "mic-sent-05658d37a13dbac8fa86a2b6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Bring everything.", "output_text": "Ms't goqwei jugwa'tu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Bring everything.", "mic_Latn": "Ms't goqwei jugwa'tu." }, "canonical_ref": "entries/m/ms't_goqwei/ms't_goqwei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f0211ae1b99e00afe76e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/ms't_goqwei/ms't_goqwei.html", "entry_url": "https://mikmaqonline.org/entries/m/ms't_goqwei/ms't_goqwei.html", "headword": "ms't_goqwei", "example_index": 0, "raw_html_path": "raw/entries/19de757848aefcdf7fdb8c3486e16ac35916fcfde52ff39a05eff59916699980.html", "raw_html_sha256": "377349032fc0c2b31c1f97cff89b7a222db39822ae169d90911b7b32c1ffcecc", "fetched_at": "2026-07-12T02:41:46.441Z", "recordings": [ { "recording_id": "16740db9db0a8bd6406fd464515e7b61c9353b2b0714bd07e0488dbfae8dbf04", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b50/b50668e23cd9fa30f47f23cc7da8b09cb9db1a2f70741c87ad7b34a82c6068d6.mp3", "archive_relative_path": "raw/audio/b50/b50668e23cd9fa30f47f23cc7da8b09cb9db1a2f70741c87ad7b34a82c6068d6.mp3" } ] } ], "prediction": "Te's goqwei te'siw.", "reference": "Ms't goqwei jugwa'tu." }, { "id": "mic-sent-05dd9c92a65e9166eb1378f4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The boy causes his dog to be wicked.", "output_text": "Lpa'tuj elue'wipnnatl ugti'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The boy causes his dog to be wicked.", "mic_Latn": "Lpa'tuj elue'wipnnatl ugti'l." }, "canonical_ref": "entries/e/elue'wipnnatl/elue'wipnnatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2e29d05ee9c4c95768d0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elue'wipnnatl/elue'wipnnatl.html", "entry_url": "https://mikmaqonline.org/entries/e/elue'wipnnatl/elue'wipnnatl.html", "headword": "elue'wipnnatl", "example_index": 0, "raw_html_path": "raw/entries/3b83973134fd59ea50d7ca3263d52106dcb3d947107e1710307907344013b01f.html", "raw_html_sha256": "ad4a8bf36709612f792fecf111d36ea38adfcb0bc739f1742d91606409749895", "fetched_at": "2026-07-12T02:37:54.444Z", "recordings": [ { "recording_id": "1c76ba8e8ac9343b598c1127661e9d67e67c5a2b98d03f060f2b52649bda5757", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1fb/1fb12395c01e3a75565a2ccdddcd8b20b27b2cc8611058259ebea0fcd6407dfa.mp3", "archive_relative_path": "raw/audio/1fb/1fb12395c01e3a75565a2ccdddcd8b20b27b2cc8611058259ebea0fcd6407dfa.mp3" } ] } ], "prediction": "Lpa'tu'ji'j gesatg ugti'l.", "reference": "Lpa'tuj elue'wipnnatl ugti'l." }, { "id": "mic-sent-060b2b9159488755b561cbd9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "How long has it been since you last filled the water bucket?", "output_text": "Tatujisa'q gi'l giaspiw ugjua'l't samqwano'q?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "How long has it been since you last filled the water bucket?", "mic_Latn": "Tatujisa'q gi'l giaspiw ugjua'l't samqwano'q?" }, "canonical_ref": "entries/g/giaspiw/giaspiw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-95d3a6cc4bb186e94c31", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/giaspiw/giaspiw.html", "entry_url": "https://mikmaqonline.org/entries/g/giaspiw/giaspiw.html", "headword": "giaspiw", "example_index": 0, "raw_html_path": "raw/entries/9c49fb255bbb6d3c4e3033544c90bce7798a603c09d887deb2b0563d206d5800.html", "raw_html_sha256": "dd894824cb0bd3870fc2be0ba6ce7ca21066cef15fe4add7df3de871b9ad8c3b", "fetched_at": "2026-07-12T02:39:28.013Z", "recordings": [ { "recording_id": "9f132ab12f6033c0330b12faaab666cef16217c3fb00046fddfc4091cb9d7bc6", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e8c/e8cc57f0eb91bfdc6a27af50afe076752c307b2358fd68050031ee4ff4460234.mp3", "archive_relative_path": "raw/audio/e8c/e8cc57f0eb91bfdc6a27af50afe076752c307b2358fd68050031ee4ff4460234.mp3" } ] } ], "prediction": "Ta'n ta'n te's gi's gaqa'tu'n tujiw pilei?", "reference": "Tatujisa'q gi'l giaspiw ugjua'l't samqwano'q?" }, { "id": "mic-sent-0653e9a2ed097863275fdd27:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I see that he/she is looking around, but I don't know what he/she is looking for.", "output_text": "Nemi'g alapteget, gatu mu gejiaq ta'n goqwei alapt'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I see that he/she is looking around, but I don't know what he/she is looking for.", "mic_Latn": "Nemi'g alapteget, gatu mu gejiaq ta'n goqwei alapt'g." }, "canonical_ref": "entries/a/alapteget/alapteget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e4efca9edc5026b744e7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/alapteget/alapteget.html", "entry_url": "https://mikmaqonline.org/entries/a/alapteget/alapteget.html", "headword": "alapteget", "example_index": 0, "raw_html_path": "raw/entries/37c03b12d733ce24fdc82d4dc4d0a0de143d9277038139a7ddb4f4059e8606b3.html", "raw_html_sha256": "8dd167f6b3f5fb2dfc829d9813d80abb37681cc4110ce01b4dfdaa485570bccf", "fetched_at": "2026-07-12T02:36:36.811Z", "recordings": [ { "recording_id": "5e9e8a1981e4326ce3d1c3b118d3b0bf39cdbca20e3f6d3c5a65113da38c0c13", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/392/3924563787f7d887015bb0b4469022d526fb1ddb5ffd63da319393391cc14fb0.mp3", "archive_relative_path": "raw/audio/392/3924563787f7d887015bb0b4469022d526fb1ddb5ffd63da319393391cc14fb0.mp3" } ] } ], "prediction": "Nemi'g nemita'latl, pas'g mu ge's goqwei ta'n goqta'toq.", "reference": "Nemi'g alapteget, gatu mu gejiaq ta'n goqwei alapt'g." }, { "id": "mic-sent-06b577415d053d8bcacd19c9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she slowly lays the infant down on the bed.", "output_text": "Sangew mesqana'latl qopisunn npo'qonigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she slowly lays the infant down on the bed.", "mic_Latn": "Sangew mesqana'latl qopisunn npo'qonigtug." }, "canonical_ref": "entries/m/mesqana'latl/mesqana'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ea0f7c46436f0bcb2062", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mesqana'latl/mesqana'latl.html", "entry_url": "https://mikmaqonline.org/entries/m/mesqana'latl/mesqana'latl.html", "headword": "mesqana'latl", "example_index": 0, "raw_html_path": "raw/entries/343f71cc278734e25fbbed51ffda4db8ac9ec207c47287c1cb3461b2d66e4839.html", "raw_html_sha256": "d43f1e91113ffeb66d5876c089e32f3a639892f1d34879c7dbb792136262285e", "fetched_at": "2026-07-12T02:41:22.833Z", "recordings": [ { "recording_id": "b4877723d00eeff126071f60ef57290185b85b5cf4f3e22d934da536f8a5f35d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0e0/0e0cdd7612f3ad8ed069c13fa88ff2cd439d45f8a8c91b2990621232a885ffa9.mp3", "archive_relative_path": "raw/audio/0e0/0e0cdd7612f3ad8ed069c13fa88ff2cd439d45f8a8c91b2990621232a885ffa9.mp3" } ] } ], "prediction": "Sangew gesatgwalatl lpa'tuj.", "reference": "Sangew mesqana'latl qopisunn npo'qonigtug." }, { "id": "mic-sent-06e79f15952d867296913ae0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she turns out differenty then what I thought.", "output_text": "Piltua'sit aq ta'n telta'siap.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she turns out differenty then what I thought.", "mic_Latn": "Piltua'sit aq ta'n telta'siap." }, "canonical_ref": "entries/p/piltua'sit/piltua'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5e1c9120e2f286acf84c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/piltua'sit/piltua'sit.html", "entry_url": "https://mikmaqonline.org/entries/p/piltua'sit/piltua'sit.html", "headword": "piltua'sit", "example_index": 0, "raw_html_path": "raw/entries/5931d033e3bc72993ad562fba6c23bfea1c1624de6307e8dbb2886e6fec708b9.html", "raw_html_sha256": "d27175355b3ce30e374fcb7cc6a957d2784d6d71b74d8a9b4f45dcb47f65c058", "fetched_at": "2026-07-12T02:43:58.349Z", "recordings": [ { "recording_id": "cf183bd59fff2726389f5ed07cb1f407bd7334790c504b6210005eb524861dee", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b04/b04bef03af1b6580f4128e5d21c265a673a0a762f9397bf59b070058cad07c2d.mp3", "archive_relative_path": "raw/audio/b04/b04bef03af1b6580f4128e5d21c265a673a0a762f9397bf59b070058cad07c2d.mp3" } ] } ], "prediction": "Newte'g na ta'n goqwei telte's'g.", "reference": "Piltua'sit aq ta'n telta'siap." }, { "id": "mic-sent-06e8fa6968e9e9c280b85869:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A shark has never swam to Listuguj.", "output_text": "Siglati mnaq Listugujg peta'mug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A shark has never swam to Listuguj.", "mic_Latn": "Siglati mnaq Listugujg peta'mug." }, "canonical_ref": "entries/s/siglati/siglati.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2959d77e2902783c16d1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/siglati/siglati.html", "entry_url": "https://mikmaqonline.org/entries/s/siglati/siglati.html", "headword": "siglati", "example_index": 0, "raw_html_path": "raw/entries/96eaa4c3f105b5945b3dd21913c5d5dda8d98abf2723e49c96d02a5f4fce6ad1.html", "raw_html_sha256": "f67c77ed8a09ec688ad7bf639582b0111e8b3dccc292ee8849af2c8651c1c0fb", "fetched_at": "2026-07-12T02:45:00.238Z", "recordings": [ { "recording_id": "5576b30c7bd77c4bdd4bda27e49bb116b439f737a4a96a905961bdef12331e3a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c1f/c1f8cfd18f2dd4ac091b696cdf7c38bf88008894563cd0cfa7787ef5bdcb26d2.mp3", "archive_relative_path": "raw/audio/c1f/c1f8cfd18f2dd4ac091b696cdf7c38bf88008894563cd0cfa7787ef5bdcb26d2.mp3" } ] } ], "prediction": "Gi's gi's lpa nugu' lugowaqan Listugujg.", "reference": "Siglati mnaq Listugujg peta'mug." }, { "id": "mic-sent-0701d39371d2f31fb46d8915:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she just now brought back my ax.", "output_text": "Aitejoq apaja'toq nutmi'gn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she just now brought back my ax.", "mic_Latn": "Aitejoq apaja'toq nutmi'gn." }, "canonical_ref": "entries/a/apaja'toq/apaja'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dbc4609f8707fb04e13c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/apaja'toq/apaja'toq.html", "entry_url": "https://mikmaqonline.org/entries/a/apaja'toq/apaja'toq.html", "headword": "apaja'toq", "example_index": 0, "raw_html_path": "raw/entries/be95600b71005db52bb2e74f1c574a4ee48566df1f6697adcfa28bc1fdb20d24.html", "raw_html_sha256": "c071aec0c12bf337ee48875f8d60585b54f9eab1f589beb4fc6a9e4a20a4891f", "fetched_at": "2026-07-12T02:37:01.479Z", "recordings": [ { "recording_id": "1b35008627c188c6817894280ab1092c2eb0204b3cb2e9970d8b96fc183295ca", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fd1/fd106091bc6fe6e05bac494dd5b172f3989c098f43b5bf7e8710b64ac62c3416.mp3", "archive_relative_path": "raw/audio/fd1/fd106091bc6fe6e05bac494dd5b172f3989c098f43b5bf7e8710b64ac62c3416.mp3" } ] } ], "prediction": "Pas'g nige' newtepa'latl nmu'ji'j.", "reference": "Aitejoq apaja'toq nutmi'gn." }, { "id": "mic-sent-071682207943f4bceeb99438:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Let us look for a plank that is nice and thick.", "output_text": "Lasqo'plaw ta'n welpase'g gwiluanej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Let us look for a plank that is nice and thick.", "mic_Latn": "Lasqo'plaw ta'n welpase'g gwiluanej." }, "canonical_ref": "entries/p/pase'g/pase'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b3450f0afa9d52078c2b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pase'g/pase'g.html", "entry_url": "https://mikmaqonline.org/entries/p/pase'g/pase'g.html", "headword": "pase'g", "example_index": 0, "raw_html_path": "raw/entries/e0304e44c89575e9a1eacaddba3ac1bf060b7baaadb0428ff1f231dce1719192.html", "raw_html_sha256": "6d4e184a28687c71d3c75b370b338cbe0056661a6c95cfe7c82899b3c2d77bcc", "fetched_at": "2026-07-12T02:43:13.423Z", "recordings": [ { "recording_id": "55b8c5dfa1df259fda7d847d767b729528475c14e984d303e22fca669d0f4277", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c02/c02667f6f7eca635aad83423382b187433a92d00f94fb6023627152bf5b5db89.mp3", "archive_relative_path": "raw/audio/c02/c02667f6f7eca635aad83423382b187433a92d00f94fb6023627152bf5b5db89.mp3" } ] } ], "prediction": "Ge' negm gi's'g ta'n tujiw gmu'j.", "reference": "Lasqo'plaw ta'n welpase'g gwiluanej." }, { "id": "mic-sent-077e7bd0eae9d7fe23e1264b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Hurry up, he/she is almost finished eating the salmon.", "output_text": "Tetaga'si geget jigpatl na plamu'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Hurry up, he/she is almost finished eating the salmon.", "mic_Latn": "Tetaga'si geget jigpatl na plamu'l." }, "canonical_ref": "entries/j/jigpatl/jigpatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-600a36b80eef834f2c96", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jigpatl/jigpatl.html", "entry_url": "https://mikmaqonline.org/entries/j/jigpatl/jigpatl.html", "headword": "jigpatl", "example_index": 0, "raw_html_path": "raw/entries/146627a4f242885f832a6db4c2e0b9210c03aa68277e4659cb88e24ff2459752.html", "raw_html_sha256": "64c74e60282c614709852f7fc80117b7c3c1fc9125f1d0a16780a8f7d56176d5", "fetched_at": "2026-07-12T02:40:18.805Z", "recordings": [ { "recording_id": "2d4c5c14ea49bfb082f317e7a3e3a96b9601781ca30f582e34e2705b368d3728", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fe8/fe87c3702a0aff9f7a3aa659c67e44956f84da17f5696c0bb866066b6e9c8c1b.mp3", "archive_relative_path": "raw/audio/fe8/fe87c3702a0aff9f7a3aa659c67e44956f84da17f5696c0bb866066b6e9c8c1b.mp3" } ] } ], "prediction": "Gi's'g, gi's gaqama'toq plamu'l.", "reference": "Tetaga'si geget jigpatl na plamu'l." }, { "id": "mic-sent-078ebbaab13d9786abb09ff5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That skunk stinks.", "output_text": "Jijjema't na apijliu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That skunk stinks.", "mic_Latn": "Jijjema't na apijliu." }, "canonical_ref": "entries/j/jijjema't/jijjema't.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dab7ca320d6960cb8dc9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jijjema't/jijjema't.html", "entry_url": "https://mikmaqonline.org/entries/j/jijjema't/jijjema't.html", "headword": "jijjema't", "example_index": 0, "raw_html_path": "raw/entries/1a6206fda91f31a5828971f13004c0b4747d04dd48d94978ccc9b1b19fd8c830.html", "raw_html_sha256": "e14ee0797235dd78ca1dd36587f9e34d2d3a46f9eb5058e2902bb6eff30139d7", "fetched_at": "2026-07-12T02:40:20.827Z", "recordings": [ { "recording_id": "3d61915f9326e19bdb2a31ddce380f81428a554b82fa1295b33cc683187577c9", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e84/e84b8a2fd1c37f02a4b541a21b3f2d4c857032f2cebd650d7a46dcc55b9c65c4.mp3", "archive_relative_path": "raw/audio/e84/e84b8a2fd1c37f02a4b541a21b3f2d4c857032f2cebd650d7a46dcc55b9c65c4.mp3" } ] } ], "prediction": "We'gwi'g na gmu'j.", "reference": "Jijjema't na apijliu." }, { "id": "mic-sent-07d31b5719b03e02c3a0f861:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Susan erases the picture.", "output_text": "Susan gasa'latl napui'gignn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Susan erases the picture.", "mic_Latn": "Susan gasa'latl napui'gignn." }, "canonical_ref": "entries/g/gasa'latl/gasa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-60ffead24900b50ca933", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gasa'latl/gasa'latl.html", "entry_url": "https://mikmaqonline.org/entries/g/gasa'latl/gasa'latl.html", "headword": "gasa'latl", "example_index": 0, "raw_html_path": "raw/entries/f90e46f3b634c749a8772d5d537baf18e471f8284be126e155cc13b0cab0200d.html", "raw_html_sha256": "ef4010045374d0827e7ad371e4bc8157ca75d736eec16b38aa2625c9d11991c9", "fetched_at": "2026-07-12T02:38:43.516Z", "recordings": [ { "recording_id": "6c20324b7cb34a6236499dbd3368098b52a21813d0044bb0ee4e76904b302411", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e84/e84c8885d44306b52c2a1854509a1c109c300df9b476f29f0e212c715d36c5cd.mp3", "archive_relative_path": "raw/audio/e84/e84c8885d44306b52c2a1854509a1c109c300df9b476f29f0e212c715d36c5cd.mp3" } ] } ], "prediction": "Susane's gesatg ta'n tujiw.", "reference": "Susan gasa'latl napui'gignn." }, { "id": "mic-sent-07e21a11e9190f4f909ca4fb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she sits nears the stove.", "output_text": "Gigjiw epsaqtejgigtug epa'sit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she sits nears the stove.", "mic_Latn": "Gigjiw epsaqtejgigtug epa'sit." }, "canonical_ref": "entries/e/epa'sit/epa'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3bbfebd743f7648512dd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/epa'sit/epa'sit.html", "entry_url": "https://mikmaqonline.org/entries/e/epa'sit/epa'sit.html", "headword": "epa'sit", "example_index": 0, "raw_html_path": "raw/entries/7fc1f5e351322d46cccd070281546bdcea952d4a8351276632dfbf30c22c2fd6.html", "raw_html_sha256": "c496c5cb31605d3fc19e3f3f8ba3f7b2739f74c3682558872ecbb58c29d0bf82", "fetched_at": "2026-07-12T02:38:06.504Z", "recordings": [ { "recording_id": "2615b4eb7c5f52c97218760fa86f46f1f3f6b91738572b7ceabcd3281859d2f1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f45/f455a7e672044ea1d76caaee4b5246f69793144626fa04efb6da490ea5329d5e.mp3", "archive_relative_path": "raw/audio/f45/f455a7e672044ea1d76caaee4b5246f69793144626fa04efb6da490ea5329d5e.mp3" } ] } ], "prediction": "E'pite'g ugta'qann.", "reference": "Gigjiw epsaqtejgigtug epa'sit." }, { "id": "mic-sent-082e37f6ea4da12145c7d966:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "How long has it been that you two are married?", "output_text": "Gi's nige' tal sa'q tepgatmoq?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "How long has it been that you two are married?", "mic_Latn": "Gi's nige' tal sa'q tepgatmoq?" }, "canonical_ref": "entries/t/tepqatg/tepqatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1c623ac0f981cc3c38ab", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tepqatg/tepqatg.html", "entry_url": "https://mikmaqonline.org/entries/t/tepqatg/tepqatg.html", "headword": "tepqatg", "example_index": 0, "raw_html_path": "raw/entries/961b7cffbad8e234448ba6c1f68a8585cff7a987534e63a13cba2688a453c92a.html", "raw_html_sha256": "9351eb153cc7cd72aa950108bcd239ad8a024df0d1c4a63986a9d787a9cf8f4d", "fetched_at": "2026-07-12T02:45:44.848Z", "recordings": [ { "recording_id": "d109fa7bbe2640e52d1039419101e6998d76a704180756008a2e9500e98d9fb8", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bce/bce1b9d8f132c601b921e5683519a775a692e64c99bef75569fa770b05eb8173.mp3", "archive_relative_path": "raw/audio/bce/bce1b9d8f132c601b921e5683519a775a692e64c99bef75569fa770b05eb8173.mp3" } ] } ], "prediction": "Ta'n ta'n te's gi's'g?", "reference": "Gi's nige' tal sa'q tepgatmoq?" }, { "id": "mic-sent-084276837fd7ea960eff9cb3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The water you get from a bubbling spring is delicious.", "output_text": "Maw wigapu'g samqwan ta'n tujiw weja'tmg tgupoqigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The water you get from a bubbling spring is delicious.", "mic_Latn": "Maw wigapu'g samqwan ta'n tujiw weja'tmg tgupoqigtug." }, "canonical_ref": "entries/t/tgupoq/tgupoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-579437580a78f2cd0b32", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tgupoq/tgupoq.html", "entry_url": "https://mikmaqonline.org/entries/t/tgupoq/tgupoq.html", "headword": "tgupoq", "example_index": 0, "raw_html_path": "raw/entries/8167bcbe440ca202bded3a02f45740c401a2fd5b01ea65a261ed632a2b678d27.html", "raw_html_sha256": "f1577b969e2282d42ff607f222cda51ec35ddf82ed243d385f9e60d100acf19e", "fetched_at": "2026-07-12T02:45:56.923Z", "recordings": [ { "recording_id": "83e009be7f55fe065949d62e4ffa74cd239c1380c14f5f0afb5aaee6d2975d27", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a74/a740d615977aaf7016ebf6d1d94483a2b7aca8856c3281ac4b13aa9b5d03e989.mp3", "archive_relative_path": "raw/audio/a74/a740d615977aaf7016ebf6d1d94483a2b7aca8856c3281ac4b13aa9b5d03e989.mp3" } ] } ], "prediction": "We'gwi'g na we'gwig ta'n tujiw gesgm'g.", "reference": "Maw wigapu'g samqwan ta'n tujiw weja'tmg tgupoqigtug." }, { "id": "mic-sent-0aa3692fe046f5865874efe4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Cut six tomatos and put them in the soup.", "output_text": "As'gom te'sijig tmato'sg tms aq pijega lasupigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Cut six tomatos and put them in the soup.", "mic_Latn": "As'gom te'sijig tmato'sg tms aq pijega lasupigtug." }, "canonical_ref": "entries/t/tmato's/tmato's.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3133060842b024d7c001", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tmato's/tmato's.html", "entry_url": "https://mikmaqonline.org/entries/t/tmato's/tmato's.html", "headword": "tmato's", "example_index": 0, "raw_html_path": "raw/entries/cdbd519352f4ddd89d7b8c499fadea9d3e4320f07e5f0584eb926d1bc3e13074.html", "raw_html_sha256": "efcdc1a72102298cf897c32a0d89015a3d3ccc437ebdc65ee32b37239e48e00c", "fetched_at": "2026-07-12T02:45:59.936Z", "recordings": [ { "recording_id": "006b166dae982f8fbb76c37e2819574a3fc9044ac246e965877381a769322343", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ec7/ec7cf08e33193e458cbea1c2ba22225020e6686c1bcb8f387be69e6dc1164167.mp3", "archive_relative_path": "raw/audio/ec7/ec7cf08e33193e458cbea1c2ba22225020e6686c1bcb8f387be69e6dc1164167.mp3" } ] } ], "prediction": "Te'sijig tetamato'q aq mesgowa'toq supugowaqan.", "reference": "As'gom te'sijig tmato'sg tms aq pijega lasupigtug." }, { "id": "mic-sent-0ab43d24cb09eef535112bc6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I was looking for my shoes, there they were in full view.", "output_text": "Algwilaqapnig nmugsng, me'su'tug episnig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I was looking for my shoes, there they were in full view.", "mic_Latn": "Algwilaqapnig nmugsng, me'su'tug episnig." }, "canonical_ref": "entries/m/me'su'tug/me'su'tug.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8d836bcc89c28de46a66", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/me'su'tug/me'su'tug.html", "entry_url": "https://mikmaqonline.org/entries/m/me'su'tug/me'su'tug.html", "headword": "me'su'tug", "example_index": 1, "raw_html_path": "raw/entries/1eb184e860d872a68872e438e332168c0bac94478c8583e1ebdde37cf1cba8e0.html", "raw_html_sha256": "521d60436383dffde6b0ff92155fc8c7019c61ea7671758f644b70d4a2d3d314", "fetched_at": "2026-07-12T02:41:24.419Z", "recordings": [ { "recording_id": "428bf48bdce06d9664e2d5ec6aefdcdf4c1e168782f1184ac18e61069c93f8fa", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6f3/6f345bfafc274ffade45eae866d8198673834e8b8cb31f9e0e2e2946b17950fd.mp3", "archive_relative_path": "raw/audio/6f3/6f345bfafc274ffade45eae866d8198673834e8b8cb31f9e0e2e2946b17950fd.mp3" } ] } ], "prediction": "Sapo'toqte'g na ntul, na te's'g.", "reference": "Algwilaqapnig nmugsng, me'su'tug episnig." }, { "id": "mic-sent-0ad2d16fef073be09000a362:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The old man is weak today.", "output_text": "Gisigu menaqanat gisgug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The old man is weak today.", "mic_Latn": "Gisigu menaqanat gisgug." }, "canonical_ref": "entries/m/menaqanat/menaqanat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-80c1c2db262d99d250f0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/menaqanat/menaqanat.html", "entry_url": "https://mikmaqonline.org/entries/m/menaqanat/menaqanat.html", "headword": "menaqanat", "example_index": 0, "raw_html_path": "raw/entries/d610175eed5ca66da65149527b6fc91445fd2e82e62ac038df282730a7be0368.html", "raw_html_sha256": "9f33ca9eb99832d2da77acb45d90d1f7568f5db8ec99a4095a351219b0bfa1e2", "fetched_at": "2026-07-12T02:41:15.297Z", "recordings": [ { "recording_id": "ba87ffd1a1d89e57d96389efb2697eea069f0ac9cbf63e4ce4d79b9e19b720fd", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bf8/bf841a1ec044ae2dad81c41fa0f168a55830f65d9e1200dcb7ec32157ebb7a7c.mp3", "archive_relative_path": "raw/audio/bf8/bf841a1ec044ae2dad81c41fa0f168a55830f65d9e1200dcb7ec32157ebb7a7c.mp3" } ] } ], "prediction": "Gisigu gisgug gisgm'g.", "reference": "Gisigu menaqanat gisgug." }, { "id": "mic-sent-0b529bf49fbabe91697f9b2c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The two of them got on top of the biggest pillows.", "output_text": "Wesgija'tijig mujga'mesgi'gewe'l tu'gwesmunn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The two of them got on top of the biggest pillows.", "mic_Latn": "Wesgija'tijig mujga'mesgi'gewe'l tu'gwesmunn." }, "canonical_ref": "entries/w/wesgija'sit/wesgija'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8b8a1c06ebbc8d3f938e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wesgija'sit/wesgija'sit.html", "entry_url": "https://mikmaqonline.org/entries/w/wesgija'sit/wesgija'sit.html", "headword": "wesgija'sit", "example_index": 0, "raw_html_path": "raw/entries/74dc8646b4c36f9f38a2b7768788b83e29d9eb68a0cd61c6e9149f3d500e87bf.html", "raw_html_sha256": "7e90fd470b4fa3f9f8900745ac6fb6632623b3a046277473b576e9427ce443a2", "fetched_at": "2026-07-12T02:47:17.137Z", "recordings": [ { "recording_id": "63181b28eead738b5373ea9e78f917b3b60a00ee9214c560eeabf7ee25005b02", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7b6/7b69a6de053c88db2f6d17e2a39187497326c0138c331a37c165f9405a99e72a.mp3", "archive_relative_path": "raw/audio/7b6/7b69a6de053c88db2f6d17e2a39187497326c0138c331a37c165f9405a99e72a.mp3" } ] } ], "prediction": "Amujpa na'te's'g'p't'p gmu'j.", "reference": "Wesgija'tijig mujga'mesgi'gewe'l tu'gwesmunn." }, { "id": "mic-sent-0ba7bceacabaf340b4f84d9c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she cooks that meat in many different ways and when it is cooked it is totally delicious.", "output_text": "Miloqs'g na wius aq gi'teg teto'qwiwigapu'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she cooks that meat in many different ways and when it is cooked it is totally delicious.", "mic_Latn": "Miloqs'g na wius aq gi'teg teto'qwiwigapu'g." }, "canonical_ref": "entries/m/miloqs'g/miloqs'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f7199a3fb2c0c626f556", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/miloqs'g/miloqs'g.html", "entry_url": "https://mikmaqonline.org/entries/m/miloqs'g/miloqs'g.html", "headword": "miloqs'g", "example_index": 0, "raw_html_path": "raw/entries/cbebd7d6c98a067d87db1c7b94b372cd16530c14b1e8cd8fb4429d05b710c146.html", "raw_html_sha256": "a56b696789a4d4a8d07dfa2d984d5cad76d1a2c3154b74ecb76f6799a76b7e11", "fetched_at": "2026-07-12T02:41:37.374Z", "recordings": [ { "recording_id": "b13cb4effdcf6176f1682f7584bdd070c27b7c5198a55391a08a6f7a9dcd0cd8", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e13/e135a661a96ec8ac39db66e13408985d59065ac347812238357e167eae866aaa.mp3", "archive_relative_path": "raw/audio/e13/e135a661a96ec8ac39db66e13408985d59065ac347812238357e167eae866aaa.mp3" } ] } ], "prediction": "Pugwelg na wi'gatig aq ta'n tujiw gisijig.", "reference": "Miloqs'g na wius aq gi'teg teto'qwiwigapu'g." }, { "id": "mic-sent-0bb8fd188b27785b934f95d8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "During the war he/she enlisted. (past tense)", "output_text": "Matntimgeg agase'wip.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "During the war he/she enlisted. (past tense)", "mic_Latn": "Matntimgeg agase'wip." }, "canonical_ref": "entries/a/agase'wit/agase'wit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7129d7f2207c29662d7f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/agase'wit/agase'wit.html", "entry_url": "https://mikmaqonline.org/entries/a/agase'wit/agase'wit.html", "headword": "agase'wit", "example_index": 0, "raw_html_path": "raw/entries/0c40882f4adeff1a33e6d8571dc803328b2c1b24d11cbeab65d9fd378162e1db.html", "raw_html_sha256": "40d198810dce91534b3229f093d5df55b8dc2b16619de687d4468ae1e1c1934d", "fetched_at": "2026-07-12T02:36:30.480Z", "recordings": [ { "recording_id": "e963f7f66b282052cb80df964c71e610e265250ecc5bd5aa0bf29d92766f6769", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6fa/6fab7c6ab133c5e0ffb9e51005391912c08ec6c6194955265f296166276a4af6.mp3", "archive_relative_path": "raw/audio/6fa/6fab7c6ab133c5e0ffb9e51005391912c08ec6c6194955265f296166276a4af6.mp3" } ] } ], "prediction": "Ta'n te's'g etlmisga'toq.", "reference": "Matntimgeg agase'wip." }, { "id": "mic-sent-0d01ee93116f105f8e445d19:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There's a big struggle going on for the Mi'gmaq language.", "output_text": "Mesgi'g matnaggewaqan wesgowa's'g ugjit Mi'gmewei tli'suti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There's a big struggle going on for the Mi'gmaq language.", "mic_Latn": "Mesgi'g matnaggewaqan wesgowa's'g ugjit Mi'gmewei tli'suti." }, "canonical_ref": "entries/m/matnaggewaqan/matnaggewaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8fac281bdbe2319027af", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/matnaggewaqan/matnaggewaqan.html", "entry_url": "https://mikmaqonline.org/entries/m/matnaggewaqan/matnaggewaqan.html", "headword": "matnaggewaqan", "example_index": 0, "raw_html_path": "raw/entries/4d21a9496ca5a752ae3aeca502c08622bd8ae471776f1672c98492179336a5f2.html", "raw_html_sha256": "24f6df0d83ddc165aa5df0fd910480617b195c48e621ca2918a39e2d0678016c", "fetched_at": "2026-07-12T02:40:55.078Z", "recordings": [ { "recording_id": "bb2083104896b26f7fdea3ccfb116745391b955c74275b21d2389bef7bb2637f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d58/d5828175568efa8026af25a65c13c77b9e3ae4cb47213ddcf9c8f38278c2f9bf.mp3", "archive_relative_path": "raw/audio/d58/d5828175568efa8026af25a65c13c77b9e3ae4cb47213ddcf9c8f38278c2f9bf.mp3" } ] } ], "prediction": "Me'gme'jig na we'gwi'g ta'n goqwei.", "reference": "Mesgi'g matnaggewaqan wesgowa's'g ugjit Mi'gmewei tli'suti." }, { "id": "mic-sent-0d653e346d0a4f1bf528d200:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Today he/she is doing business across the river.", "output_text": "Gisgug qame'g wejo'tasit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Today he/she is doing business across the river.", "mic_Latn": "Gisgug qame'g wejo'tasit." }, "canonical_ref": "entries/w/wejo'tasit/wejo'tasit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-acaff9d75b7acef1a279", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejo'tasit/wejo'tasit.html", "entry_url": "https://mikmaqonline.org/entries/w/wejo'tasit/wejo'tasit.html", "headword": "wejo'tasit", "example_index": 0, "raw_html_path": "raw/entries/4d685ba14f572fbcf7c6dde2288c36c57aa57ef2fdff5f8e68d9d56da8aec508.html", "raw_html_sha256": "a7875e0b0c580ed24e0e12036886df959912725caf9eb22f8d322b63bef859b8", "fetched_at": "2026-07-12T02:46:55.847Z", "recordings": [ { "recording_id": "f5b23e94c4fc23451cd689fb89f0f409488e87fb0749ad47348977fee938f767", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f44/f444bd5d1c7063f980b79430e99212c02913a6835a970c0f94fd0cc58ba5e87b.mp3", "archive_relative_path": "raw/audio/f44/f444bd5d1c7063f980b79430e99212c02913a6835a970c0f94fd0cc58ba5e87b.mp3" } ] } ], "prediction": "Gisgug negm etlgwigtug.", "reference": "Gisgug qame'g wejo'tasit." }, { "id": "mic-sent-0d7d3590a76595b3ffe76a06:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The flower floats on the river.", "output_text": "Wasueg ala'lugweg sipug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The flower floats on the river.", "mic_Latn": "Wasueg ala'lugweg sipug." }, "canonical_ref": "entries/a/ala'lugweg/ala'lugweg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-01f3f55bd955026f7490", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/ala'lugweg/ala'lugweg.html", "entry_url": "https://mikmaqonline.org/entries/a/ala'lugweg/ala'lugweg.html", "headword": "ala'lugweg", "example_index": 0, "raw_html_path": "raw/entries/d6cb3ba05697f384eacb875925c852273d34f0da39a262ad0a6d6db4a4c21a0f.html", "raw_html_sha256": "a6f9cfc050455b24ee2c74df683d8ddd7ec44d7a6e78fb2a98331148dd800bb9", "fetched_at": "2026-07-12T02:36:34.097Z", "recordings": [ { "recording_id": "eece15e4faadd306a3ef3d5f77913aa8ffb113f1484b588223671b24f7319b88", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/726/726449cd874a0017d90cfe67d293861093828d4a4ceaa1e571e7ec4554d0e691.mp3", "archive_relative_path": "raw/audio/726/726449cd874a0017d90cfe67d293861093828d4a4ceaa1e571e7ec4554d0e691.mp3" } ] } ], "prediction": "Pugwelg'p etlmisga'toq ugjit.", "reference": "Wasueg ala'lugweg sipug." }, { "id": "mic-sent-0d88cf0dd8f90619b6d7cc4d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My heel is blistering and it is hurting me.", "output_text": "Wijgwe'jua'sit nqon aq gesnuguit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My heel is blistering and it is hurting me.", "mic_Latn": "Wijgwe'jua'sit nqon aq gesnuguit." }, "canonical_ref": "entries/w/wijgwe'jua'sit/wijgwe'jua'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1fc5cd658f2ab469a097", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wijgwe'jua'sit/wijgwe'jua'sit.html", "entry_url": "https://mikmaqonline.org/entries/w/wijgwe'jua'sit/wijgwe'jua'sit.html", "headword": "wijgwe'jua'sit", "example_index": 0, "raw_html_path": "raw/entries/140b451b0e174ca657ec1217f993d6d57357d9490e4080d760dc3feba38d250c.html", "raw_html_sha256": "7da75930e6042eb2261851f928dc2666161acedb4d688a1e5e3667447b6c1907", "fetched_at": "2026-07-12T02:47:33.222Z", "recordings": [ { "recording_id": "11a330f1cefbf64f454ed90cb427d3cbba375cb2f243131156899adefeb584f1", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ddc/ddc5380075ba0a65ce0dcba7bd0b3b6decb95f5433d8ef8f4b4794ab3db1a7ab.mp3", "archive_relative_path": "raw/audio/ddc/ddc5380075ba0a65ce0dcba7bd0b3b6decb95f5433d8ef8f4b4794ab3db1a7ab.mp3" } ] } ], "prediction": "Pugwelg na nugu'n aq mesgi'g.", "reference": "Wijgwe'jua'sit nqon aq gesnuguit." }, { "id": "mic-sent-0d9e7c1e5ebee20a070ad5a4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who's mincing the onions now?", "output_text": "Wen nugjaqsajig pse's'sg nige'?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who's mincing the onions now?", "mic_Latn": "Wen nugjaqsajig pse's'sg nige'?" }, "canonical_ref": "entries/n/nugjaqsatl/nugjaqsatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-86fa0e026c859d528f6a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nugjaqsatl/nugjaqsatl.html", "entry_url": "https://mikmaqonline.org/entries/n/nugjaqsatl/nugjaqsatl.html", "headword": "nugjaqsatl", "example_index": 0, "raw_html_path": "raw/entries/3ad97147c899a6db9a4ecc3971b0ccd8e0f404622529bd7e067c729c4690e1c8.html", "raw_html_sha256": "7a097f483a27451fd0a6cbbc31610a26f3b3e7f7953fa4563e83fbd80ff0a626", "fetched_at": "2026-07-12T02:42:44.368Z", "recordings": [ { "recording_id": "3b883879dd608f94a145b32f606fa88d4e1cd74ca5f58c9e403422731c8c674e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a01/a01734f59f4a711d5bc98429adc93ce689597113d01ae2caa7edb7178fe23104.mp3", "archive_relative_path": "raw/audio/a01/a01734f59f4a711d5bc98429adc93ce689597113d01ae2caa7edb7178fe23104.mp3" } ] } ], "prediction": "Wen na'te's'g lugowaqan nige'?", "reference": "Wen nugjaqsajig pse's'sg nige'?" }, { "id": "mic-sent-0dbfc2cff1c89bd89c1bafa3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Was it him/her that you said is unskilled?", "output_text": "Negm na telue's'p awane'jit?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Was it him/her that you said is unskilled?", "mic_Latn": "Negm na telue's'p awane'jit?" }, "canonical_ref": "entries/a/awane'jit/awane'jit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9ac84faca79d0f454b28", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/awane'jit/awane'jit.html", "entry_url": "https://mikmaqonline.org/entries/a/awane'jit/awane'jit.html", "headword": "awane'jit", "example_index": 0, "raw_html_path": "raw/entries/dfdceabaa3b04d01bdcaadd186541bff84d07396b9ed66e030c95ee6e3c65933.html", "raw_html_sha256": "4400fadf998da22f218f09ff64ddf9f4b130a8503f60d6530d2612531ccd4b39", "fetched_at": "2026-07-12T02:37:28.389Z", "recordings": [ { "recording_id": "d43f4d74ed6ec4a05cc031c6818de52abf3748187e78e56b1f881f1daeb08956", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d8d/d8da7020e652f3e16e3bb04f4dc5f9e693c3e5d68925a016c5daa6970cba1ebf.mp3", "archive_relative_path": "raw/audio/d8d/d8da7020e652f3e16e3bb04f4dc5f9e693c3e5d68925a016c5daa6970cba1ebf.mp3" } ] } ], "prediction": "Gi'l na telte'lmu'j?", "reference": "Negm na telue's'p awane'jit?" }, { "id": "mic-sent-0e073bfe08746bf87959ea01:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she walks to the woods through deep snow.", "output_text": "Elasumteget nipugtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she walks to the woods through deep snow.", "mic_Latn": "Elasumteget nipugtug." }, "canonical_ref": "entries/e/elasumteget/elasumteget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-cae67b0e89b754dc3694", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elasumteget/elasumteget.html", "entry_url": "https://mikmaqonline.org/entries/e/elasumteget/elasumteget.html", "headword": "elasumteget", "example_index": 0, "raw_html_path": "raw/entries/d81f070a330e3d5ddb06c3fbde44ac977845cc837dd50b92ab417aadf7180cea.html", "raw_html_sha256": "70b2e8c8770b32881119214956b7afc29f03e6e1dfc67e71e8586689f61ae1df", "fetched_at": "2026-07-12T02:37:40.462Z", "recordings": [ { "recording_id": "26f1b87ca880ffa0ca5c1f1a66221885eedc6909a51ebfa1263111900f1a4107", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cca/ccadf0d8278a7768bd939092f26c8c3d01f0484a44d82293231776c59a7a459f.mp3", "archive_relative_path": "raw/audio/cca/ccadf0d8278a7768bd939092f26c8c3d01f0484a44d82293231776c59a7a459f.mp3" } ] } ], "prediction": "Pugwelg'p na gmu'ji'j gesgm'g.", "reference": "Elasumteget nipugtug." }, { "id": "mic-sent-0e19d9cfe6845c3dc20234b3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That man coming in has a scarred face.", "output_text": "Wisigwat na ji'nm wejgwipisgwa't.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That man coming in has a scarred face.", "mic_Latn": "Wisigwat na ji'nm wejgwipisgwa't." }, "canonical_ref": "entries/w/wisigwat/wisigwat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-727faf065b708ec9e7d1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wisigwat/wisigwat.html", "entry_url": "https://mikmaqonline.org/entries/w/wisigwat/wisigwat.html", "headword": "wisigwat", "example_index": 0, "raw_html_path": "raw/entries/132ad2446f66c66298c8558b5a3cf18c252bc2b87e36233e135652b9860acd4d.html", "raw_html_sha256": "88718b1364638ce9623c9d346f852912634f5c4b14aedfab6e132dec4bc31951", "fetched_at": "2026-07-12T02:47:39.150Z", "recordings": [ { "recording_id": "f590e2444148135823df9a9f6e13283fe9caca7168e8e79ed5b95c169c13f405", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6d3/6d34e26e7a20dc059f4c2fb1b92b96940e15e571f60b6e9902ab0adffaff2949.mp3", "archive_relative_path": "raw/audio/6d3/6d34e26e7a20dc059f4c2fb1b92b96940e15e571f60b6e9902ab0adffaff2949.mp3" } ] } ], "prediction": "Na ji'nm gisga'sit na ji'n.", "reference": "Wisigwat na ji'nm wejgwipisgwa't." }, { "id": "mic-sent-0ea6dc913403f367b5abdf7d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It is dangerous along the edge of a cliff.", "output_text": "Nsanoqonig gigjiw enmipgowe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It is dangerous along the edge of a cliff.", "mic_Latn": "Nsanoqonig gigjiw enmipgowe'g." }, "canonical_ref": "entries/e/enmipgowe'g/enmipgowe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-37ca2455649ebb392f5d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/enmipgowe'g/enmipgowe'g.html", "entry_url": "https://mikmaqonline.org/entries/e/enmipgowe'g/enmipgowe'g.html", "headword": "enmipgowe'g", "example_index": 0, "raw_html_path": "raw/entries/cc44eb54bc8f4874042aeffaf58e988e120b0af724415d14af102314ee31c522.html", "raw_html_sha256": "23928ee79d62b807603da573e86a23e6161c74c84baf2c972cafc2505c4edfb3", "fetched_at": "2026-07-12T02:38:02.990Z", "recordings": [ { "recording_id": "5c7e25a688ca3327d0b2751bfd33823cef2132981545f24fc5376ef2399dd900", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/60b/60be5f048ce24d72bf239247ba262222f5772828b7de2dc37b5d6884228f6e52.mp3", "archive_relative_path": "raw/audio/60b/60be5f048ce24d72bf239247ba262222f5772828b7de2dc37b5d6884228f6e52.mp3" } ] } ], "prediction": "We'gwi'jig ta'n tujiw gisi'g.", "reference": "Nsanoqonig gigjiw enmipgowe'g." }, { "id": "mic-sent-0edac0e74eb253cc39c7855f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Erika is happy today.", "output_text": "Erika weljesing gisgug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Erika is happy today.", "mic_Latn": "Erika weljesing gisgug." }, "canonical_ref": "entries/w/weljesing/weljesing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9b57473345382c04e865", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/weljesing/weljesing.html", "entry_url": "https://mikmaqonline.org/entries/w/weljesing/weljesing.html", "headword": "weljesing", "example_index": 0, "raw_html_path": "raw/entries/85daf857bb47e9c1ff4a6df8415b497b9ac7d9c4631c5231a39e0e61fbe370b4.html", "raw_html_sha256": "b10b8fd6e4aa4594be34a9359b1773b493583709ddd9a0148e68a9e09b66c6e1", "fetched_at": "2026-07-12T02:47:04.786Z", "recordings": [ { "recording_id": "2786c2bdea06e5fbd9ee1442d3967256b76bca36cf236edd3e05ddf7176a4fb9", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/322/32234cfc2f1739dd7aa9b53580ad35af344b0976d670b8b3f6a30ca5b0812d80.mp3", "archive_relative_path": "raw/audio/322/32234cfc2f1739dd7aa9b53580ad35af344b0976d670b8b3f6a30ca5b0812d80.mp3" } ] } ], "prediction": "Erika gesatg gisgug.", "reference": "Erika weljesing gisgug." }, { "id": "mic-sent-0f61be68ba72bcbb66d24663:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "If you sew scrapes of cloth together, you can make a nice blanket.", "output_text": "Mawi'smn piwsignn, gisites gelu'lg a'su'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "If you sew scrapes of cloth together, you can make a nice blanket.", "mic_Latn": "Mawi'smn piwsignn, gisites gelu'lg a'su'n." }, "canonical_ref": "entries/p/piwsign/piwsign.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-44fd40e6773bb4317559", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/piwsign/piwsign.html", "entry_url": "https://mikmaqonline.org/entries/p/piwsign/piwsign.html", "headword": "piwsign", "example_index": 0, "raw_html_path": "raw/entries/d61bf303316e1504dba7a1bf2a3d178375f5373b1c691fd7e8fa44028673cc7b.html", "raw_html_sha256": "a3c704dc36059386b6ad5afac871e5c0ffc21ba48c52564d2d89088a53a0f3f2", "fetched_at": "2026-07-12T02:44:11.211Z", "recordings": [ { "recording_id": "0b00dbf913883c188f0596b7e57710524208b199dd06807be048ca062cc74217", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/719/719b3031400abf1da30a0f0a19b1e3f1fcc302307f44198a681d3e7d3cc771fc.mp3", "archive_relative_path": "raw/audio/719/719b3031400abf1da30a0f0a19b1e3f1fcc302307f44198a681d3e7d3cc771fc.mp3" } ] } ], "prediction": "Pugwelg'p'ti'l, gatu gmu'j gisipi'g.", "reference": "Mawi'smn piwsignn, gisites gelu'lg a'su'n." }, { "id": "mic-sent-0fff239348c680e7196e0c4f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has always exaggerated what he/she says about him/her.", "output_text": "Pana ne'gaw gi'gatagnimatl", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has always exaggerated what he/she says about him/her.", "mic_Latn": "Pana ne'gaw gi'gatagnimatl" }, "canonical_ref": "entries/g/gi'gatagnimatl/gi'gatagnimatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-73bae35c809aac2a090d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gi'gatagnimatl/gi'gatagnimatl.html", "entry_url": "https://mikmaqonline.org/entries/g/gi'gatagnimatl/gi'gatagnimatl.html", "headword": "gi'gatagnimatl", "example_index": 0, "raw_html_path": "raw/entries/e3287136f4354f35c438b170a5e0fd69dccddd82549918911669a551b88ea67f.html", "raw_html_sha256": "4fd9704842d8a40a0ff65c2e2193f5969f723866bf5d5acef8d5b9c092610bac", "fetched_at": "2026-07-12T02:39:29.620Z", "recordings": [ { "recording_id": "a27ce4a3a8f8aa21117409934f4ced842666df4ac27c5f50636a93cf289dc87b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1e4/1e44bd8d4b5eceb6dbb863a264eb0a8f8d3f2a27e4d5f8f5735a9ec765d511dd.mp3", "archive_relative_path": "raw/audio/1e4/1e44bd8d4b5eceb6dbb863a264eb0a8f8d3f2a27e4d5f8f5735a9ec765d511dd.mp3" } ] } ], "prediction": "Te's te'sijig ta'n goqwei telimatl.", "reference": "Pana ne'gaw gi'gatagnimatl" }, { "id": "mic-sent-1001f0392de54cb9ce840ccc:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she will encourage me when I'm not feeling good.", "output_text": "Nijipjulit ta'n tujiw mu welo'tegew.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she will encourage me when I'm not feeling good.", "mic_Latn": "Nijipjulit ta'n tujiw mu welo'tegew." }, "canonical_ref": "entries/n/nijipjulatl/nijipjulatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b1709126fa05288c2f4d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nijipjulatl/nijipjulatl.html", "entry_url": "https://mikmaqonline.org/entries/n/nijipjulatl/nijipjulatl.html", "headword": "nijipjulatl", "example_index": 0, "raw_html_path": "raw/entries/5c6b6b2f53f80def9ca39ff912e56236a53722365a4a4e4cab6834a429043506.html", "raw_html_sha256": "2dc321abcecd10f1f81b211eeccc50cd6281eb9f91aedbc44f39fea3057d0226", "fetched_at": "2026-07-12T02:42:33.706Z", "recordings": [ { "recording_id": "bcc831765d03534ecc0c4cdc933f504b048ba736838b9293288ca116487e6194", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5c2/5c20c199e45bc92e1a8e44ec3f52241561588df7ee44c359e6d9d29d5596fb00.mp3", "archive_relative_path": "raw/audio/5c2/5c20c199e45bc92e1a8e44ec3f52241561588df7ee44c359e6d9d29d5596fb00.mp3" } ] } ], "prediction": "Amujpa ni'n ta'n tujiw maljewe'g.", "reference": "Nijipjulit ta'n tujiw mu welo'tegew." }, { "id": "mic-sent-104d4310b1bbed184b380238:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's to bad that he/she didn't cut that board correctly.", "output_text": "Ansue'g na mu' tetapu'sagul na lasqo'plawl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's to bad that he/she didn't cut that board correctly.", "mic_Latn": "Ansue'g na mu' tetapu'sagul na lasqo'plawl." }, "canonical_ref": "entries/t/tetapu'satl/tetapu'satl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4fb0739a27b90af2dbec", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tetapu'satl/tetapu'satl.html", "entry_url": "https://mikmaqonline.org/entries/t/tetapu'satl/tetapu'satl.html", "headword": "tetapu'satl", "example_index": 0, "raw_html_path": "raw/entries/e3c7e792dc4da1fbb4b929ce24bd85c54684dbf13d9fb5e55ab7979f24fef5ba.html", "raw_html_sha256": "f39ea553e1ebba75efd1ceda1697f8134faca680679f97e248fff0cd1f450625", "fetched_at": "2026-07-12T02:45:48.091Z", "recordings": [ { "recording_id": "53ea438f35da8000e4584dc0e0b36d86e1acba19a572d281fd767e79cc9a98ba", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2b5/2b57878d57e0b1423c49c4b83211a16026fc2d5da25c6acc0a7685fa6955cc9d.mp3", "archive_relative_path": "raw/audio/2b5/2b57878d57e0b1423c49c4b83211a16026fc2d5da25c6acc0a7685fa6955cc9d.mp3" } ] } ], "prediction": "We'gwi'g ta'n tujiw nugu' gesatg na lpa'toq.", "reference": "Ansue'g na mu' tetapu'sagul na lasqo'plawl." }, { "id": "mic-sent-1098c66eb7b17d4a756bcb21:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That little brook flows from the lake.", "output_text": "Ala sipu'ji'j qospemg wejijuig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That little brook flows from the lake.", "mic_Latn": "Ala sipu'ji'j qospemg wejijuig." }, "canonical_ref": "entries/w/wejijuig/wejijuig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8fd61cbd4039a96d7599", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejijuig/wejijuig.html", "entry_url": "https://mikmaqonline.org/entries/w/wejijuig/wejijuig.html", "headword": "wejijuig", "example_index": 0, "raw_html_path": "raw/entries/4b183108499e0f8912a2df8bc141dc5d5e40fcdb93af35a796b2672b7714fa2a.html", "raw_html_sha256": "9c58655705e6f6e7c279cd5e2b2eec214b282ff1a0e8e8ca59413829d79eaba5", "fetched_at": "2026-07-12T02:36:30.177Z", "recordings": [ { "recording_id": "2fac8a68cbc6c1be88bb9be40487f63943ae48b09f0cb5fe4cb165838b65409a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9f6/9f62a912c3f61befc02afc8c881302c514678856dd5ad91a847c7d0dd116d96e.mp3", "archive_relative_path": "raw/audio/9f6/9f62a912c3f61befc02afc8c881302c514678856dd5ad91a847c7d0dd116d96e.mp3" } ] } ], "prediction": "Na p'te'ji'j na gmu'j gesatg.", "reference": "Ala sipu'ji'j qospemg wejijuig." }, { "id": "mic-sent-109c021f64cec36391b607ce:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's calming down now, it was so stormy before.", "output_text": "Ewupniaq gatu, tewjimtu'na'qapneg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's calming down now, it was so stormy before.", "mic_Latn": "Ewupniaq gatu, tewjimtu'na'qapneg." }, "canonical_ref": "entries/e/ewupniaq/ewupniaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-05742cb6f815b1c88b00", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/ewupniaq/ewupniaq.html", "entry_url": "https://mikmaqonline.org/entries/e/ewupniaq/ewupniaq.html", "headword": "ewupniaq", "example_index": 0, "raw_html_path": "raw/entries/1e8294bb0d7acd0a85f14f90348f0997144251dba3d2d526a2389dc1e86024d6.html", "raw_html_sha256": "6b1790f7b3186f566b4be53b72dfaced1c7895380d4c600dc5e208f3bd7d8929", "fetched_at": "2026-07-12T02:38:34.057Z", "recordings": [ { "recording_id": "139ac6c431e27efad915745669dc02e93621bb271e84e5d9b4a3ea20e6aa62ca", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9ef/9efa287d54308379d6d1e390f93d7f77db9148897ccdfe60651b9de6e3f96335.mp3", "archive_relative_path": "raw/audio/9ef/9efa287d54308379d6d1e390f93d7f77db9148897ccdfe60651b9de6e3f96335.mp3" } ] } ], "prediction": "Gi's nige' pas'g, te's gesgm'g.", "reference": "Ewupniaq gatu, tewjimtu'na'qapneg." }, { "id": "mic-sent-10a3039c25972824ffb00bdd:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I forget his/her name, he/she lives at the cove end of Listuguj and is a good baker.", "output_text": "Awanta'si ugwisunm, wanne'ge wigit aq nata'toqtet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I forget his/her name, he/she lives at the cove end of Listuguj and is a good baker.", "mic_Latn": "Awanta'si ugwisunm, wanne'ge wigit aq nata'toqtet." }, "canonical_ref": "entries/n/nata'toqtet/nata'toqtet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-35c23253e683a6af667f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nata'toqtet/nata'toqtet.html", "entry_url": "https://mikmaqonline.org/entries/n/nata'toqtet/nata'toqtet.html", "headword": "nata'toqtet", "example_index": 0, "raw_html_path": "raw/entries/4dccfa72d3d7705cf11bf174abebace3f0f7b942d50bfe95c5f78c9ae7253417.html", "raw_html_sha256": "de7b49bcb740a36a41838935efb105f500b1aba23398b002fead706e7ecf9399", "fetched_at": "2026-07-12T02:42:11.191Z", "recordings": [ { "recording_id": "7da21e5e0521c6f2acd637b1029a2df9cde7fe3e3043cdd7c72f559e31bda3ed", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b00/b00cb82dd76a48c37fbfd8a227ed317f1b507336a24fdc616da0d8d98aa19779.mp3", "archive_relative_path": "raw/audio/b00/b00cb82dd76a48c37fbfd8a227ed317f1b507336a24fdc616da0d8d98aa19779.mp3" } ] } ], "prediction": "Nemi'g ugjit, Listugujg ugta'qann aq we'gwign.", "reference": "Awanta'si ugwisunm, wanne'ge wigit aq nata'toqtet." }, { "id": "mic-sent-10b5ff63920925b2a881140a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is eating and working at the same time.", "output_text": "Etlmijjit aq nespilugwet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is eating and working at the same time.", "mic_Latn": "Etlmijjit aq nespilugwet." }, "canonical_ref": "entries/n/nespilugwet/nespilugwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-48d55b46172c6852b96d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nespilugwet/nespilugwet.html", "entry_url": "https://mikmaqonline.org/entries/n/nespilugwet/nespilugwet.html", "headword": "nespilugwet", "example_index": 0, "raw_html_path": "raw/entries/1054ddab57cdf6c2278518e800d6a31f0d28bc57882643cc806a346417843bc5.html", "raw_html_sha256": "d0d03124e35ef6689ff9566201133b62a38e716681a7f21320dab975abc2dd1a", "fetched_at": "2026-07-12T02:42:22.658Z", "recordings": [ { "recording_id": "8860d8aee9ff1fa8253930daf2b4c5e62e700f15bab75d08d52cb7e77cc3884c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/022/022bb67c96a93cc66e501a4e96e52271a4b8bf27e9334bacf64ca2c4917e1de3.mp3", "archive_relative_path": "raw/audio/022/022bb67c96a93cc66e501a4e96e52271a4b8bf27e9334bacf64ca2c4917e1de3.mp3" } ] } ], "prediction": "Gi's etlma'toq aq lugowa'sit.", "reference": "Etlmijjit aq nespilugwet." }, { "id": "mic-sent-110eed9af76ea71f24a8840a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This morning I found a moose's bed.", "output_text": "Sepei we'jitaq tia'm unpan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This morning I found a moose's bed.", "mic_Latn": "Sepei we'jitaq tia'm unpan." }, "canonical_ref": "entries/u/unpan/unpan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-78629079a0b7c78e6cd3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/unpan/unpan.html", "entry_url": "https://mikmaqonline.org/entries/u/unpan/unpan.html", "headword": "unpan", "example_index": 0, "raw_html_path": "raw/entries/dfbc4d5bf85557d8fb8d3ec4125553c04f8f285d7ddfbd7f2280273e1627a9e9.html", "raw_html_sha256": "42c94ed9091ccb5de08b7fcf184b8c16707ae0a713cba2b5d71090d267af32cc", "fetched_at": "2026-07-12T02:36:03.179Z", "recordings": [ { "recording_id": "bb504e0aa03d2d35e2875551da6faa95c748517290df3a56b478be1b8a45707b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/159/159c0477580f70ba3bc5315380a065118d9385eac5b1502b570059f7bcd92217.mp3", "archive_relative_path": "raw/audio/159/159c0477580f70ba3bc5315380a065118d9385eac5b1502b570059f7bcd92217.mp3" } ] } ], "prediction": "Gisgugsitpu'g etlmisga'toq.", "reference": "Sepei we'jitaq tia'm unpan." }, { "id": "mic-sent-11c5732f2efabef3959218d5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Just look for the large round pieces of firewood.", "output_text": "Pas'g maqa'q pugsug gwile'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Just look for the large round pieces of firewood.", "mic_Latn": "Pas'g maqa'q pugsug gwile'n." }, "canonical_ref": "entries/m/maqa'q/maqa'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b46dfe47ed563453f7c6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/maqa'q/maqa'q.html", "entry_url": "https://mikmaqonline.org/entries/m/maqa'q/maqa'q.html", "headword": "maqa'q", "example_index": 0, "raw_html_path": "raw/entries/d3461153d49fe19ec535ac7f29507313d5385b9dc1a4f19488477737cdfa8431.html", "raw_html_sha256": "df10c20b18b19562855e46e59e6b9451dd28fdc880e0f1eaad8bab792d3ee461", "fetched_at": "2026-07-12T02:40:49.459Z", "recordings": [ { "recording_id": "d640dbbaebf880c96d612d7305d34f973702d70abbaa82662f8ac084a1ed1200", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/28d/28d03b979a48909eb76dbde8383beb417c6d8a7c204fdb0637b38735ee933a18.mp3", "archive_relative_path": "raw/audio/28d/28d03b979a48909eb76dbde8383beb417c6d8a7c204fdb0637b38735ee933a18.mp3" } ] } ], "prediction": "Pas'g gesgm'g ta'n tujiw gmu'j.", "reference": "Pas'g maqa'q pugsug gwile'n." }, { "id": "mic-sent-11f2cf553cebfeccc9e57b15:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The moose hunter ambushes the animal.", "output_text": "Nujitia'mue'get gis(i)gimteluatl wi'sisl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The moose hunter ambushes the animal.", "mic_Latn": "Nujitia'mue'get gis(i)gimteluatl wi'sisl." }, "canonical_ref": "entries/g/gimteluatl/gimteluatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e07db20a20b76e082631", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gimteluatl/gimteluatl.html", "entry_url": "https://mikmaqonline.org/entries/g/gimteluatl/gimteluatl.html", "headword": "gimteluatl", "example_index": 0, "raw_html_path": "raw/entries/29da70de74d7dc6b503c3cdf0d274bd14d2b87372e153797ed8bc176c29ded34.html", "raw_html_sha256": "3c82eadc07ca2ec9a19186b2cb98d65ce28a33b17a1c0954d36aca8587f1ee8b", "fetched_at": "2026-07-12T02:39:33.332Z", "recordings": [ { "recording_id": "a3c78e7ddac9457cd94f728a4d0063113cd5f3b25ec09c78f3ac8e831afe69b2", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/25d/25dbf23556dc3fc7fd12ff530518ba7d7ecfb28124ec21c2cba705a3f8edd263.mp3", "archive_relative_path": "raw/audio/25d/25dbf23556dc3fc7fd12ff530518ba7d7ecfb28124ec21c2cba705a3f8edd263.mp3" } ] } ], "prediction": "Nmu'ji'j gesatg ugjit lpa'tu'n.", "reference": "Nujitia'mue'get gis(i)gimteluatl wi'sisl." }, { "id": "mic-sent-1209ecccc5f4bceee6c42efa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Just one card is enough.", "output_text": "Pas'g newte'jit la'sgw tepiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Just one card is enough.", "mic_Latn": "Pas'g newte'jit la'sgw tepiet." }, "canonical_ref": "entries/t/tepiet/tepiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4fb35297389ab7eadc54", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tepiet/tepiet.html", "entry_url": "https://mikmaqonline.org/entries/t/tepiet/tepiet.html", "headword": "tepiet", "example_index": 0, "raw_html_path": "raw/entries/a95beae42c613fc77f383ed336f6ab5782d2ebf2d42c707ae99646200b61bf5c.html", "raw_html_sha256": "9dd8e86b402e44638568cf8324e2bbf5b6f95a206bded4c7d0f96706b21cdf81", "fetched_at": "2026-07-12T02:45:42.442Z", "recordings": [ { "recording_id": "126a7759a656a53b42569d909b606bb37b440f38ccb0cbdc7ce5dd597f2c8577", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9bd/9bdd78a57172d7125a1a7be60b986b69d8b125dc003c1d1333721cc6933265e0.mp3", "archive_relative_path": "raw/audio/9bd/9bdd78a57172d7125a1a7be60b986b69d8b125dc003c1d1333721cc6933265e0.mp3" } ] } ], "prediction": "Pas'g pas'g newte'l gaqa'toq.", "reference": "Pas'g newte'jit la'sgw tepiet." }, { "id": "mic-sent-12bfbf059e6a85d8aef8949d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where do you fish for scallops?", "output_text": "Tami etligtanujig sasqale'sg?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where do you fish for scallops?", "mic_Latn": "Tami etligtanujig sasqale'sg?" }, "canonical_ref": "entries/s/sasqale's/sasqale's.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-175472e342af2ab3ba26", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sasqale's/sasqale's.html", "entry_url": "https://mikmaqonline.org/entries/s/sasqale's/sasqale's.html", "headword": "sasqale's", "example_index": 0, "raw_html_path": "raw/entries/9e365a8c3fd854b407c75e5875e890fd0ae2f03b5373f57ec65884836a50e3c6.html", "raw_html_sha256": "762c3e30c886e6a0b4eb15c9c6390bbda13cb804f6c8f947b96d3043c0d7741c", "fetched_at": "2026-07-12T02:44:45.977Z", "recordings": [ { "recording_id": "e2117c2cf88fba5d7390d4a2d89fb2a5ae362e36a821b5c2f0747c9085594f48", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/793/793716a9a39c5447af825dee11329882393397179f48f1588a9939ac9de03eea.mp3", "archive_relative_path": "raw/audio/793/793716a9a39c5447af825dee11329882393397179f48f1588a9939ac9de03eea.mp3" } ] } ], "prediction": "Tami we'gwi'g'p na gmu'j?", "reference": "Tami etligtanujig sasqale'sg?" }, { "id": "mic-sent-1304a31e3c914c1a12eee209:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The sun is pretty when it's setting.", "output_text": "Welamugsit na na'gu'set ta'n tujiw galqwasiej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The sun is pretty when it's setting.", "mic_Latn": "Welamugsit na na'gu'set ta'n tujiw galqwasiej." }, "canonical_ref": "entries/g/galqwasiet/galqwasiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-00f2581afc2eb7edf644", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/galqwasiet/galqwasiet.html", "entry_url": "https://mikmaqonline.org/entries/g/galqwasiet/galqwasiet.html", "headword": "galqwasiet", "example_index": 0, "raw_html_path": "raw/entries/18795f5462d260fb86a8d8f89f5dc2609150dce1786611e4d2d305978bc2b033.html", "raw_html_sha256": "6919d84c900fad9ecb439fa37d927d5d2780f49f26acfc2bca905457a770e7ed", "fetched_at": "2026-07-12T02:38:35.462Z", "recordings": [ { "recording_id": "1984f4ae1baab5bc7b698a8fe57c770042664b8c16dc5dcbb252ce906475ca78", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e98/e9858cfc7feea50daff38325d5676e8e8858e8888271d07b9905d448e599343a.mp3", "archive_relative_path": "raw/audio/e98/e9858cfc7feea50daff38325d5676e8e8858e8888271d07b9905d448e599343a.mp3" } ] } ], "prediction": "We'gwi'g na we'gwig ta'n tujiw pas'g.", "reference": "Welamugsit na na'gu'set ta'n tujiw galqwasiej." }, { "id": "mic-sent-13b3b82e08cd3e2daa1a4ef5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she rubs butter onto the cake pan.", "output_text": "Mlageju'mi eljaqq gogosigna'gwigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she rubs butter onto the cake pan.", "mic_Latn": "Mlageju'mi eljaqq gogosigna'gwigtug." }, "canonical_ref": "entries/e/eljaqq/eljaqq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e83da8d15be819017cae", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/eljaqq/eljaqq.html", "entry_url": "https://mikmaqonline.org/entries/e/eljaqq/eljaqq.html", "headword": "eljaqq", "example_index": 0, "raw_html_path": "raw/entries/73ba07ebb9d056b393bfb56d472547173071c6f170bf2869380b4646541685e7.html", "raw_html_sha256": "1302cd4d429bd2c80a31eb2b27dc106b01e481fbd71cae54b7cbdd25fbeb8788", "fetched_at": "2026-07-12T02:37:48.020Z", "recordings": [ { "recording_id": "4996e10134feb3e9353501742cfa7cdca2952f760866434e82e861bddc0e54ff", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6ab/6ab074d17222d620e269b73b570d6870642881db3e95fcfc3908c5ebb54facf4.mp3", "archive_relative_path": "raw/audio/6ab/6ab074d17222d620e269b73b570d6870642881db3e95fcfc3908c5ebb54facf4.mp3" } ] } ], "prediction": "Pugwelg na plamu'g ugtaqan.", "reference": "Mlageju'mi eljaqq gogosigna'gwigtug." }, { "id": "mic-sent-13c5bbbfb6a8086992998b7e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What color is that, is it black or is it navy blue?", "output_text": "Talamu'g na, maqtawe'g gisna maqtawiewne'g?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What color is that, is it black or is it navy blue?", "mic_Latn": "Talamu'g na, maqtawe'g gisna maqtawiewne'g?" }, "canonical_ref": "entries/m/maqtawe'g/maqtawe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-13519d10316c989b0a6f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/maqtawe'g/maqtawe'g.html", "entry_url": "https://mikmaqonline.org/entries/m/maqtawe'g/maqtawe'g.html", "headword": "maqtawe'g", "example_index": 0, "raw_html_path": "raw/entries/a9ce9378d67d1d89cfa14175180980df99bc602bc85eea54e4abd03764a7f470.html", "raw_html_sha256": "abbd035b3f9d01191274de0fb9d7787b22e9ee0fbc0abad3a4decb0d6add3ed3", "fetched_at": "2026-07-12T02:40:51.462Z", "recordings": [ { "recording_id": "7cf2efd0d7863f118acca8ce6301a36dec5ec1781139f26735b4a5bca40433b0", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a10/a108d3d8ac089fa5aad1c9bdf80545417917f4cd1f24e8d43fa0dd3e200d2464.mp3", "archive_relative_path": "raw/audio/a10/a108d3d8ac089fa5aad1c9bdf80545417917f4cd1f24e8d43fa0dd3e200d2464.mp3" } ] } ], "prediction": "Ta's'g na lpa, wesgm'g aq wesgmu'g?", "reference": "Talamu'g na, maqtawe'g gisna maqtawiewne'g?" }, { "id": "mic-sent-15dceac53877fb073229b23f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where did he/she get that cat?", "output_text": "Tami weja'latl na gajue'wjl?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where did he/she get that cat?", "mic_Latn": "Tami weja'latl na gajue'wjl?" }, "canonical_ref": "entries/w/weja'latl/weja'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-19cde957393e533ec453", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/weja'latl/weja'latl.html", "entry_url": "https://mikmaqonline.org/entries/w/weja'latl/weja'latl.html", "headword": "weja'latl", "example_index": 0, "raw_html_path": "raw/entries/6b738f93388b09f43413918d051fe940c947a40b05543606bc245cbd5453f70e.html", "raw_html_sha256": "583a26879ad0b1ff7beae5c78d4c25b813197d7c8953ac0008d2126397649e0d", "fetched_at": "2026-07-12T02:46:47.794Z", "recordings": [ { "recording_id": "c2a7aca5b7e526e6e6cfd1e8cafd1b5d32d8e4397e5c72ef131bbd21fc1a4eba", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e01/e011e883b7fd3f0def17a8ffcce81ed6d0b817d506de322f550b464f3f23096f.mp3", "archive_relative_path": "raw/audio/e01/e011e883b7fd3f0def17a8ffcce81ed6d0b817d506de322f550b464f3f23096f.mp3" } ] } ], "prediction": "Tami eteg na gajuei?", "reference": "Tami weja'latl na gajue'wjl?" }, { "id": "mic-sent-164c23aed61151f3167b8c7d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Let my clothes dry some more they're still damp.", "output_text": "Nutapsun siawipiatej me nenmue'gl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Let my clothes dry some more they're still damp.", "mic_Latn": "Nutapsun siawipiatej me nenmue'gl." }, "canonical_ref": "entries/n/nenmue'g/nenmue'g.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f1bf171e85952e336d1e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nenmue'g/nenmue'g.html", "entry_url": "https://mikmaqonline.org/entries/n/nenmue'g/nenmue'g.html", "headword": "nenmue'g", "example_index": 1, "raw_html_path": "raw/entries/b68f21699798feb36e1253e78cdd54151b7e707d1a22a9039e87c3c27ae89ef9.html", "raw_html_sha256": "93e7a2c07181cbc874538c1fdc3596c5651af8168f57fd3dc9584a9e1c87d593", "fetched_at": "2026-07-12T02:42:19.330Z", "recordings": [ { "recording_id": "31e6e846ed2ccf788bee1cce48d03e8ab4fc8ad22e88dada531444542f26398a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fb3/fb3e86072a7236434f6e611960b19f0c3d931d89ded40c377ae869f435be5909.mp3", "archive_relative_path": "raw/audio/fb3/fb3e86072a7236434f6e611960b19f0c3d931d89ded40c377ae869f435be5909.mp3" } ] } ], "prediction": "Pilei nige' mimaji'j nmu'j gisijig.", "reference": "Nutapsun siawipiatej me nenmue'gl." }, { "id": "mic-sent-167c58fa8563a5d14305d741:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My girlfriend is chopping kindling.", "output_text": "Nitape'sgw etliaps'sqate'get.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My girlfriend is chopping kindling.", "mic_Latn": "Nitape'sgw etliaps'sqate'get." }, "canonical_ref": "entries/a/aps'sqate'get/aps'sqate'get.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-100f60012b51ce54e627", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/aps'sqate'get/aps'sqate'get.html", "entry_url": "https://mikmaqonline.org/entries/a/aps'sqate'get/aps'sqate'get.html", "headword": "aps'sqate'get", "example_index": 0, "raw_html_path": "raw/entries/7d8999f65a3d5e811f62ac073d5e079616481f0abbd3f5afd21f6b0d5188d414.html", "raw_html_sha256": "793e53559fbaeb3c38a123e5a43d807640e26bd980d3dc8f3d5ecd7854a12674", "fetched_at": "2026-07-12T02:37:11.340Z", "recordings": [ { "recording_id": "225fed0fbb70428c5029f1d4aa6aa27db0526c2e0418b7f33a8c808e3a9a12d2", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/336/336f533dee632b07b89408a3f26d145e750c671c52c50852e1c7b5baa5510286.mp3", "archive_relative_path": "raw/audio/336/336f533dee632b07b89408a3f26d145e750c671c52c50852e1c7b5baa5510286.mp3" } ] } ], "prediction": "Nitap etlmisga'latl.", "reference": "Nitape'sgw etliaps'sqate'get." }, { "id": "mic-sent-16884811a938804da71027fa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There's very good weather in the month of May.", "output_text": "Na tepgunset sqoljuigu's maw-weligisg'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There's very good weather in the month of May.", "mic_Latn": "Na tepgunset sqoljuigu's maw-weligisg'g." }, "canonical_ref": "entries/s/sqoljuigu's/sqoljuigu's.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-de788313987fa1a802f6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sqoljuigu's/sqoljuigu's.html", "entry_url": "https://mikmaqonline.org/entries/s/sqoljuigu's/sqoljuigu's.html", "headword": "sqoljuigu's", "example_index": 0, "raw_html_path": "raw/entries/1e8b802412b8928443a1788b3370e9286e0256dadb61551b9aacd28f94e5e330.html", "raw_html_sha256": "40c02f8820ce364f9c00fbbe1b5aaf6b4d3650db582641d3e939795a95458930", "fetched_at": "2026-07-12T02:45:14.704Z", "recordings": [ { "recording_id": "aa315f8cdb8f772536fc4af14052244eed4d830e3baba97853c99c3d9349aa39", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a52/a52d559e863129f54920225918f82cd2119dcfb35f7e4f465404d6c8a2e04198.mp3", "archive_relative_path": "raw/audio/a52/a52d559e863129f54920225918f82cd2119dcfb35f7e4f465404d6c8a2e04198.mp3" } ] } ], "prediction": "Me'gwig na mawjitu'g.", "reference": "Na tepgunset sqoljuigu's maw-weligisg'g." }, { "id": "mic-sent-16f37749ec52a035aaeca6dc:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Joseph delivers wood.", "output_text": "So'sep nutateji'putoq pugsug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Joseph delivers wood.", "mic_Latn": "So'sep nutateji'putoq pugsug." }, "canonical_ref": "entries/n/nutateji'putoq/nutateji'putoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9b34c9ed1adc95ff8739", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nutateji'putoq/nutateji'putoq.html", "entry_url": "https://mikmaqonline.org/entries/n/nutateji'putoq/nutateji'putoq.html", "headword": "nutateji'putoq", "example_index": 0, "raw_html_path": "raw/entries/4400a9f191d72744ce78c73f4fcae7ccbf8d7d432b24c4f8a74a9b45b503489f.html", "raw_html_sha256": "bb58ef54c61fb68712cf6aff82383e09fe3de64d417bf3234109dbf7e3eb2726", "fetched_at": "2026-07-12T02:42:56.013Z", "recordings": [ { "recording_id": "4fbd0171b0bdfebc4ebfc7673d6482ba0c2fc689dac2672bdff8a451b5c2c187", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bf6/bf6aecc697c9aa543d7d26c5389412e6b9693e28d01fb7fe9a9fcf27d3b6ca77.mp3", "archive_relative_path": "raw/audio/bf6/bf6aecc697c9aa543d7d26c5389412e6b9693e28d01fb7fe9a9fcf27d3b6ca77.mp3" } ] } ], "prediction": "So'sep gesatg ugjit.", "reference": "So'sep nutateji'putoq pugsug." }, { "id": "mic-sent-17f18b36f85c0c1f0511d6d7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I think the one rearranging everthing is making it all crooked.", "output_text": "Ala etlilo'tasit etug istuo'toq ms't goqwei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I think the one rearranging everthing is making it all crooked.", "mic_Latn": "Ala etlilo'tasit etug istuo'toq ms't goqwei." }, "canonical_ref": "entries/i/istua'toq/istua'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-97e814378cdbd83f4a66", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/istua'toq/istua'toq.html", "entry_url": "https://mikmaqonline.org/entries/i/istua'toq/istua'toq.html", "headword": "istua'toq", "example_index": 0, "raw_html_path": "raw/entries/aa1591851ad9ea3b57da07bc9b239d6e8e47858e3d6b1b7b8372432db6559ccc.html", "raw_html_sha256": "f593b768f917a6eccf61ebeb0005d1dec6a9d2b4ae9ea960e028027e8d8902e3", "fetched_at": "2026-07-12T02:40:11.689Z", "recordings": [ { "recording_id": "6d743f1cc1c1411836363f10375c4e27adb21af8ba0cf3f30bbb7104d4df53c1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c4d/c4d77ab6aa9642181b4c87f2777bcb97c42366ea474adca1d5e758287b95fd1c.mp3", "archive_relative_path": "raw/audio/c4d/c4d77ab6aa9642181b4c87f2777bcb97c42366ea474adca1d5e758287b95fd1c.mp3" } ] } ], "prediction": "Telte's'g ta'n te'sipowtoq te's goqwei gesatg.", "reference": "Ala etlilo'tasit etug istuo'toq ms't goqwei." }, { "id": "mic-sent-182663baaa86166fed5212fb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My aunt dresses the baby.", "output_text": "Nsugwis gegno'tlatl mijua'ji'tl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My aunt dresses the baby.", "mic_Latn": "Nsugwis gegno'tlatl mijua'ji'tl." }, "canonical_ref": "entries/g/gegno'tlatl/gegno'tlatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-400d7e2e3314ff2a0110", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gegno'tlatl/gegno'tlatl.html", "entry_url": "https://mikmaqonline.org/entries/g/gegno'tlatl/gegno'tlatl.html", "headword": "gegno'tlatl", "example_index": 0, "raw_html_path": "raw/entries/7cbd1d7efa153c61a6da57b7c0ccd2507a3b8d77ad086c876717f82fe19e93f4.html", "raw_html_sha256": "6110e4e6458c3b9fbaea46edf8ced499a08ebf7f06ee235a11e94764d4dd1a05", "fetched_at": "2026-07-12T02:38:49.240Z", "recordings": [ { "recording_id": "3245960d6191b2fee8caebe20d0886112efa64b56a610ae34229dcf6e4fd8f0e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2b5/2b5f9f67f0f52509f7fd3c470a613357d4a6dc6b3a32d2a0bd377999f840e8fb.mp3", "archive_relative_path": "raw/audio/2b5/2b5f9f67f0f52509f7fd3c470a613357d4a6dc6b3a32d2a0bd377999f840e8fb.mp3" } ] } ], "prediction": "Ntlume'ji'j na'te'l.", "reference": "Nsugwis gegno'tlatl mijua'ji'tl." }, { "id": "mic-sent-18582136e89bfac83c79a3b6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Name three breakfast foods.", "output_text": "Wi'tmui ne'sisgl egsitpu'gwatalmgewe'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Name three breakfast foods.", "mic_Latn": "Wi'tmui ne'sisgl egsitpu'gwatalmgewe'l." }, "canonical_ref": "entries/e/egsitpu'gwatalmgewei/egsitpu'gwatalmgewei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f106552d92f359f77a1e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/egsitpu'gwatalmgewei/egsitpu'gwatalmgewei.html", "entry_url": "https://mikmaqonline.org/entries/e/egsitpu'gwatalmgewei/egsitpu'gwatalmgewei.html", "headword": "egsitpu'gwatalmgewei", "example_index": 0, "raw_html_path": "raw/entries/7fa591f86602239a5ba38ca6b38262f16112e7830d6d92fd6a91a84f2e82ff6f.html", "raw_html_sha256": "33c1ca974732ed688fe177c7d9ecd6f5d130cb3608e5285b9ae6396c2f527aea", "fetched_at": "2026-07-12T02:37:31.096Z", "recordings": [ { "recording_id": "880d3750d09c36f050bb200e33109000841c64f94e0d57c2f8967a27c5b391da", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fa2/fa2563def86b704b504bc4b8ef7adee388ec6386522580d252da524329f5c806.mp3", "archive_relative_path": "raw/audio/fa2/fa2563def86b704b504bc4b8ef7adee388ec6386522580d252da524329f5c806.mp3" } ] } ], "prediction": "Ge's'g ta'n te'sipowji'jg.", "reference": "Wi'tmui ne'sisgl egsitpu'gwatalmgewe'l." }, { "id": "mic-sent-1889126a82a63e12c7b4a9f7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has finally sewn his/her net.", "output_text": "Glapis gatu gisi'satl ugta'piml.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has finally sewn his/her net.", "mic_Latn": "Glapis gatu gisi'satl ugta'piml." }, "canonical_ref": "entries/g/gisi'satl/gisi'satl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a4edd993fcad92c2b738", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gisi'satl/gisi'satl.html", "entry_url": "https://mikmaqonline.org/entries/g/gisi'satl/gisi'satl.html", "headword": "gisi'satl", "example_index": 0, "raw_html_path": "raw/entries/cca256c8edd075daf6c7b1f1fa0d04f39bec1e37230cc33b96f5ab8abff45d81.html", "raw_html_sha256": "03745d27e2a888f57ee6c79b4f37ae329333e4303c26ba81b36ceb4014aad485", "fetched_at": "2026-07-12T02:39:40.176Z", "recordings": [ { "recording_id": "5a24e58d9c5709df83b595ccd28d31a5c68a73c52d7ec7c3c046edfd408cbf5d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4ac/4ac2fde47106c936a8ee8dcbf15792fd01c28388fb5a9dffd6c3db62b487b427.mp3", "archive_relative_path": "raw/audio/4ac/4ac2fde47106c936a8ee8dcbf15792fd01c28388fb5a9dffd6c3db62b487b427.mp3" } ] } ], "prediction": "Gi's gi's gisi'g ugta'latl ugjitl.", "reference": "Glapis gatu gisi'satl ugta'piml." }, { "id": "mic-sent-18accec4093fc7ec505b85e1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You are standing in the foreground of this photograph.", "output_text": "E'tmapuguin ula napui'gignigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You are standing in the foreground of this photograph.", "mic_Latn": "E'tmapuguin ula napui'gignigtug." }, "canonical_ref": "entries/e/e'tmapuguit/e'tmapuguit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-21cdb52f708bc9bc6662", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/e'tmapuguit/e'tmapuguit.html", "entry_url": "https://mikmaqonline.org/entries/e/e'tmapuguit/e'tmapuguit.html", "headword": "e'tmapuguit", "example_index": 0, "raw_html_path": "raw/entries/56d9052d91fab634d73fb38e288b74ff50997d31741700cd3130ae09f1bf3dae.html", "raw_html_sha256": "0c9c9cdccdd7e670f7b9fce656507fbb260fbd03579ad39b515d8a68ead480d3", "fetched_at": "2026-07-12T02:38:26.106Z", "recordings": [ { "recording_id": "ee50e9311a73482ececabbc0e70773014b1b164795d64f5c09e64f2f8cf1d547", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/859/859dbf902d81a5bda1d1980c1d11a43b05c690401eb5f04d30f11417a24d7dcf.mp3", "archive_relative_path": "raw/audio/859/859dbf902d81a5bda1d1980c1d11a43b05c690401eb5f04d30f11417a24d7dcf.mp3" } ] } ], "prediction": "Pugwelg'p na ula pilei.", "reference": "E'tmapuguin ula napui'gignigtug." }, { "id": "mic-sent-18bf9baab72ae0651a9b4761:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is barely able to stand up anymore.", "output_text": "Waqgajgis'pugua'sit nugu'.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is barely able to stand up anymore.", "mic_Latn": "Waqgajgis'pugua'sit nugu'." }, "canonical_ref": "entries/w/waqgaj/waqgaj.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2585b89812c3244dbbe1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waqgaj/waqgaj.html", "entry_url": "https://mikmaqonline.org/entries/w/waqgaj/waqgaj.html", "headword": "waqgaj", "example_index": 0, "raw_html_path": "raw/entries/516194d736db988a26971fe866c4c486c14c1e44c61b58fba23b3280718b52af.html", "raw_html_sha256": "fae77b5bf67368baf6b72e78ac8294c272657cf48306585e225895ed195b1671", "fetched_at": "2026-07-12T02:46:41.167Z", "recordings": [ { "recording_id": "427fe2ad88054980fcd8e945040cc5eca3d29fb29fb0ac5360c1d66ad84b5a13", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/21f/21f187689f78b949d6cb484a31ea80a91365f0f3a3e9954535dfd0003f10cea6.mp3", "archive_relative_path": "raw/audio/21f/21f187689f78b949d6cb484a31ea80a91365f0f3a3e9954535dfd0003f10cea6.mp3" } ] } ], "prediction": "Gi's nige' newte'g.", "reference": "Waqgajgis'pugua'sit nugu'." }, { "id": "mic-sent-1900665031cd1a35153615ac:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little girl is trying to reach her doll.", "output_text": "E'pite'ji'j wejitepnatl ugtapsute'ganml.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little girl is trying to reach her doll.", "mic_Latn": "E'pite'ji'j wejitepnatl ugtapsute'ganml." }, "canonical_ref": "entries/w/wejitepnatl/wejitepnatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3d8936da02b6978b0d5b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejitepnatl/wejitepnatl.html", "entry_url": "https://mikmaqonline.org/entries/w/wejitepnatl/wejitepnatl.html", "headword": "wejitepnatl", "example_index": 0, "raw_html_path": "raw/entries/8be356ebc36a27e981429b5659f7fc3495652c615d1aa5a9894057b27b77e3e6.html", "raw_html_sha256": "b2fe81d8b48b5cd5b18e75ead4283a01dd897727095cac18d7e21201b2e98b37", "fetched_at": "2026-07-12T02:46:55.244Z", "recordings": [ { "recording_id": "b7e71abaab03fd476c4f677c9521c1e2f06f2a3885461ba213d665107a716b9e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e84/e84de4ede926b5533b1fc8b98cac5ec772c112032514befcda9d3e61460e20fe.mp3", "archive_relative_path": "raw/audio/e84/e84de4ede926b5533b1fc8b98cac5ec772c112032514befcda9d3e61460e20fe.mp3" } ] } ], "prediction": "E'pite'ji'j gesatg ugjit ugjit.", "reference": "E'pite'ji'j wejitepnatl ugtapsute'ganml." }, { "id": "mic-sent-190bc826027e6e9997f3e651:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You have been rocking in that rocking chair and knitting all day, no wonder you got a lot of knitting done.", "output_text": "Suel newtigisg'g nanamien jitlo'mugwaqanigtug aq etlisgnuen, getl ta na mesgi'g gisisgnuatmn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You have been rocking in that rocking chair and knitting all day, no wonder you got a lot of knitting done.", "mic_Latn": "Suel newtigisg'g nanamien jitlo'mugwaqanigtug aq etlisgnuen, getl ta na mesgi'g gisisgnuatmn." }, "canonical_ref": "entries/n/nanamiet/nanamiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-57dcd8cb7a2d244c0202", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nanamiet/nanamiet.html", "entry_url": "https://mikmaqonline.org/entries/n/nanamiet/nanamiet.html", "headword": "nanamiet", "example_index": 0, "raw_html_path": "raw/entries/c02ed9225184a0526ab983c832d1c6dce4924feb6e518e4aa39fd820b0a1d5e3.html", "raw_html_sha256": "8fceffdacceb607daefc21df816f7f60d2089eb0a212893495f00e59888ded0b", "fetched_at": "2026-07-12T02:41:57.770Z", "recordings": [ { "recording_id": "95d5652e817f87725b2ce16e0d1ece1e2faec1c42514eb15fec16c847e26e75e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6cb/6cb40fc75607919483c5834cd174dfad8da9db08c5ed341d4825b1a56ef69fa8.mp3", "archive_relative_path": "raw/audio/6cb/6cb40fc75607919483c5834cd174dfad8da9db08c5ed341d4825b1a56ef69fa8.mp3" } ] } ], "prediction": "Gi's gi's jugwa'si'g na tujiw pile'gig, mu' newte'g ta'n te's gaqamijig.", "reference": "Suel newtigisg'g nanamien jitlo'mugwaqanigtug aq etlisgnuen, getl ta na mesgi'g gisisgnuatmn." }, { "id": "mic-sent-1999a158da2b595da7012465:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she dug the last potato out of the ground.", "output_text": "Lpa getalqigwalatl ugtejgewe'l tap'tann maqamigewigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she dug the last potato out of the ground.", "mic_Latn": "Lpa getalqigwalatl ugtejgewe'l tap'tann maqamigewigtug." }, "canonical_ref": "entries/g/getalqigwalatl/getalqigwalatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-145f25b4f8197620b0b2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/getalqigwalatl/getalqigwalatl.html", "entry_url": "https://mikmaqonline.org/entries/g/getalqigwalatl/getalqigwalatl.html", "headword": "getalqigwalatl", "example_index": 0, "raw_html_path": "raw/entries/6c8733f23a28b7f1a3403b660a78b373398157ffe548ca4b7c54e2de3751589f.html", "raw_html_sha256": "5ae25f9d9765fb05240fc1228cc7674e45e91a1716eb1502e3ad14ba5637a457", "fetched_at": "2026-07-12T02:39:19.676Z", "recordings": [ { "recording_id": "983f3089c586d938897f74558b666a2a8bb51a7b35a29e45166cc31401f4efc6", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/542/5423caaa5e8be1b350d968bd550d60173cbd62278bb39ade1f15bc38695b0b4a.mp3", "archive_relative_path": "raw/audio/542/5423caaa5e8be1b350d968bd550d60173cbd62278bb39ade1f15bc38695b0b4a.mp3" } ] } ], "prediction": "Newte'g'p ugjit ugjit pata'toq.", "reference": "Lpa getalqigwalatl ugtejgewe'l tap'tann maqamigewigtug." }, { "id": "mic-sent-19a596dcd96e5ea51a59d7e6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "At first we thought the house didn't look strong enough (structurally).", "output_text": "Amsgweseweieg amalaptmeg'p na wenji'guom.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "At first we thought the house didn't look strong enough (structurally).", "mic_Latn": "Amsgweseweieg amalaptmeg'p na wenji'guom." }, "canonical_ref": "entries/a/amalapt'g/amalapt'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b653859fd78ece518c99", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amalapt'g/amalapt'g.html", "entry_url": "https://mikmaqonline.org/entries/a/amalapt'g/amalapt'g.html", "headword": "amalapt'g", "example_index": 0, "raw_html_path": "raw/entries/298ad68105ace7eb105a1436bda27e453c3d6748732bb6de02bcd2449e69fb2f.html", "raw_html_sha256": "b2b9ff14be78ed0265fec6ac54efd2e510d2f2c8297adfe34970434532543063", "fetched_at": "2026-07-12T02:36:46.264Z", "recordings": [ { "recording_id": "6ea43e0f304c53085492a4e185a179038bd1f29e73a0648b8b44e2d1bf4c1c1f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6e2/6e25a4669354223ab18eb763c86cf9c760842b132fb8be9f856b491e9d7566ff.mp3", "archive_relative_path": "raw/audio/6e2/6e25a4669354223ab18eb763c86cf9c760842b132fb8be9f856b491e9d7566ff.mp3" } ] } ], "prediction": "Amujpa ni'n telte'lmu'tm na wenji'guomg.", "reference": "Amsgweseweieg amalaptmeg'p na wenji'guom." }, { "id": "mic-sent-19a764a0401b4b73d52dc965:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she knows how to crochet.", "output_text": "Nata'amalisgnuet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she knows how to crochet.", "mic_Latn": "Nata'amalisgnuet." }, "canonical_ref": "entries/a/amalisgnuet/amalisgnuet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6a30b4519983ca81115f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amalisgnuet/amalisgnuet.html", "entry_url": "https://mikmaqonline.org/entries/a/amalisgnuet/amalisgnuet.html", "headword": "amalisgnuet", "example_index": 0, "raw_html_path": "raw/entries/2fca8e5b8ed714c493b4d7e33c5addd2f2be622d844d93b628e2519709371297.html", "raw_html_sha256": "95966cee34505024cb98ce382ff9d497acc15b179c85049ac4a6409c2ee2c944", "fetched_at": "2026-07-12T02:36:46.956Z", "recordings": [ { "recording_id": "4fb893e47c8fb4d1ac935ed1097dc38adf8a940c1c1fb94fa9759288b9d67983", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f8a/f8afd2d96ed5ab04aa1437aab5a51223c7fc5893f05d0ec68a1d2c4c945e84ad.mp3", "archive_relative_path": "raw/audio/f8a/f8afd2d96ed5ab04aa1437aab5a51223c7fc5893f05d0ec68a1d2c4c945e84ad.mp3" } ] } ], "prediction": "Amujpa ta'n tujiw gisijig.", "reference": "Nata'amalisgnuet." }, { "id": "mic-sent-19c13f3f4daeb8651f248196:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I've arrived for nothing, I've missed every single thing.", "output_text": "Pisuiw pegisin, gaqa mes'tesgmaneg ta'n te's'g goqwei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I've arrived for nothing, I've missed every single thing.", "mic_Latn": "Pisuiw pegisin, gaqa mes'tesgmaneg ta'n te's'g goqwei." }, "canonical_ref": "entries/p/pisuiw/pisuiw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-cf54cb0d0194345aae0a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pisuiw/pisuiw.html", "entry_url": "https://mikmaqonline.org/entries/p/pisuiw/pisuiw.html", "headword": "pisuiw", "example_index": 0, "raw_html_path": "raw/entries/4c4593d279145025d8972cf039e099f52b386c6550863e4051dc9197e716f91d.html", "raw_html_sha256": "3e54f5ad87673aa9e913ddfbaf846a11006d984bd86949fffee1e0c0470c898d", "fetched_at": "2026-07-12T02:44:05.584Z", "recordings": [ { "recording_id": "098dc86434a98b4d4760a5aaa6b3352463427f6fe7f2382826a0f7e606e6f103", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1d4/1d4f009999c855dbee605d2747024356a18797d8b100b54996a60f8898154fbe.mp3", "archive_relative_path": "raw/audio/1d4/1d4f009999c855dbee605d2747024356a18797d8b100b54996a60f8898154fbe.mp3" } ] } ], "prediction": "Mu ni'n te'sipow, te's goqwei ta'n tujiw.", "reference": "Pisuiw pegisin, gaqa mes'tesgmaneg ta'n te's'g goqwei." }, { "id": "mic-sent-19d649a6f2e72c85879d5885:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend changes (demeanor) very fast.", "output_text": "Jaqalsa'se'wa'sit na ula nitap.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend changes (demeanor) very fast.", "mic_Latn": "Jaqalsa'se'wa'sit na ula nitap." }, "canonical_ref": "entries/s/sa'se'wa'sit/sa'se'wa'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3b438243d315a7736427", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sa'se'wa'sit/sa'se'wa'sit.html", "entry_url": "https://mikmaqonline.org/entries/s/sa'se'wa'sit/sa'se'wa'sit.html", "headword": "sa'se'wa'sit", "example_index": 0, "raw_html_path": "raw/entries/d340e44636e8f2fa8a023f7bc1dc4018ec967456694f56a1f1dfb879e55f132b.html", "raw_html_sha256": "44346abb25712ad9fad636d1d0412b0f322f2a0326ea4c138f47d53fd631a3a1", "fetched_at": "2026-07-12T02:44:44.553Z", "recordings": [ { "recording_id": "5e7a44da13d55294e69bfee1d4ea8c52a1691ff7c506e2546ff80a7250f4c181", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fe8/fe81739cc188c84e6cd67ee61c54153c0fc46f665d2730d70cc6f9ce2102966e.mp3", "archive_relative_path": "raw/audio/fe8/fe81739cc188c84e6cd67ee61c54153c0fc46f665d2730d70cc6f9ce2102966e.mp3" } ] } ], "prediction": "Nitap na mawja'toq.", "reference": "Jaqalsa'se'wa'sit na ula nitap." }, { "id": "mic-sent-19ed14d261e7ae8f20675c8c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My name is Tio'tis.", "output_text": "Ni'n teluisi Tio'tis", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My name is Tio'tis.", "mic_Latn": "Ni'n teluisi Tio'tis" }, "canonical_ref": "entries/n/ni'n/ni'n.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a68f6c25bb5401b7963c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ni'n/ni'n.html", "entry_url": "https://mikmaqonline.org/entries/n/ni'n/ni'n.html", "headword": "ni'n", "example_index": 0, "raw_html_path": "raw/entries/74c614080bc9b949059241a8b1f29565096acaffe183b597dcecc43eebd2b283.html", "raw_html_sha256": "87a6b22099e65a205e83c89c0b199c044c4d24f1fd1de044f1df81c899adbb71", "fetched_at": "2026-07-12T02:42:34.007Z", "recordings": [ { "recording_id": "3b8e92804ffbb782cea931ecf9502f2fb2086fd429a745fa1636d071bf6aed16", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c09/c0971dba9b8cb92804a0f3d55a97d8e973041d99368f7f7301db9447229e7e33.mp3", "archive_relative_path": "raw/audio/c09/c0971dba9b8cb92804a0f3d55a97d8e973041d99368f7f7301db9447229e7e33.mp3" } ] } ], "prediction": "Tio'tis nige' ni'n.", "reference": "Ni'n teluisi Tio'tis" }, { "id": "mic-sent-1b140b36453a071d818f918c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's been fixed for a long time.", "output_text": "Gi's sa'q gisa'tas'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's been fixed for a long time.", "mic_Latn": "Gi's sa'q gisa'tas'g." }, "canonical_ref": "entries/g/gisa'tas'g/gisa'tas'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a9368d0fa75b001266b4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gisa'tas'g/gisa'tas'g.html", "entry_url": "https://mikmaqonline.org/entries/g/gisa'tas'g/gisa'tas'g.html", "headword": "gisa'tas'g", "example_index": 0, "raw_html_path": "raw/entries/f99b50cd85d94cf1265215104a4971a2bb1544d32ff1dd565ee283bf4c26a7e9.html", "raw_html_sha256": "fe5ea0c39813d06eb5b8220ac7044e5a4288d349dff822728a4a5787b609eb63", "fetched_at": "2026-07-12T02:39:36.258Z", "recordings": [ { "recording_id": "48d8aca531f0bc5b00bb1a9addab2045e85ceb9c23940cec01f526e4496eca6b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2d6/2d60fd320292638800cea43e870e37bf042be55bb40ee3a98ac7b9faeab62027.mp3", "archive_relative_path": "raw/audio/2d6/2d60fd320292638800cea43e870e37bf042be55bb40ee3a98ac7b9faeab62027.mp3" } ] } ], "prediction": "Gi's gi's gaqa'toq.", "reference": "Gi's sa'q gisa'tas'g." }, { "id": "mic-sent-1ee47b34ac3872be7ec641a2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There's our friend over there, running through the muddy water!", "output_text": "Sisguapuigtug ala pemtugwi'g gigmenu!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There's our friend over there, running through the muddy water!", "mic_Latn": "Sisguapuigtug ala pemtugwi'g gigmenu!" }, "canonical_ref": "entries/s/sisguapu/sisguapu.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e1e185d78a4642edcad5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sisguapu/sisguapu.html", "entry_url": "https://mikmaqonline.org/entries/s/sisguapu/sisguapu.html", "headword": "sisguapu", "example_index": 0, "raw_html_path": "raw/entries/b25db256de95b6c466eae057aa1dfbf4f74a8ff1d2b04be8b2702f2223964afb.html", "raw_html_sha256": "76bab39b14d1b7486654d8e0ab0cce425e7a5ee3234eb63ba34c5fc7a10d0368", "fetched_at": "2026-07-12T02:45:07.698Z", "recordings": [ { "recording_id": "a1fca52e66e17e20f71e1923b4a821c33f792473de57e95bb19a9bdafe239487", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/865/865d847067d26a65f7e4ed918751a85a1fd2c85a45b1c4f750f50e225da2603a.mp3", "archive_relative_path": "raw/audio/865/865d847067d26a65f7e4ed918751a85a1fd2c85a45b1c4f750f50e225da2603a.mp3" } ] } ], "prediction": "Ala na ula nitap ala, lpa gmu'ji'j!", "reference": "Sisguapuigtug ala pemtugwi'g gigmenu!" }, { "id": "mic-sent-1f1c1c3596514acdbd0512b6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Did you (plural) go night sailing last night.", "output_text": "Nipaqtega'tioqos wela'gwe'g?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Did you (plural) go night sailing last night.", "mic_Latn": "Nipaqtega'tioqos wela'gwe'g?" }, "canonical_ref": "entries/n/nipaqteget/nipaqteget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9d8071f2fd3bf6dcac00", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nipaqteget/nipaqteget.html", "entry_url": "https://mikmaqonline.org/entries/n/nipaqteget/nipaqteget.html", "headword": "nipaqteget", "example_index": 0, "raw_html_path": "raw/entries/bf177965c36ff3027331e4fc9fb29caf4098515fba55d38334dbc10dba45922f.html", "raw_html_sha256": "d052d10f5d3b622147158618980e6e581f79d46c9f5ac95bc098d66e44fb82ae", "fetched_at": "2026-07-12T02:36:03.229Z", "recordings": [ { "recording_id": "7bbd223f93f5b04711736635a3cedd7cec89269c54ad0e9c13499c2b75b7160e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b51/b5156418891bdce14af1d0548ccccb78fea555898a2ef798c655889f605ce0da.mp3", "archive_relative_path": "raw/audio/b51/b5156418891bdce14af1d0548ccccb78fea555898a2ef798c655889f605ce0da.mp3" } ] } ], "prediction": "Gi's gi's'g wela'gwe'g.", "reference": "Nipaqtega'tioqos wela'gwe'g?" }, { "id": "mic-sent-1f2f9233fff53517e25ff072:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Bring the broth and a spoon to me.", "output_text": "P'tew aq amqwanji'j jugwa'tuwi.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Bring the broth and a spoon to me.", "mic_Latn": "P'tew aq amqwanji'j jugwa'tuwi." }, "canonical_ref": "entries/a/amqwanji'j/amqwanji'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9a53bdd38bde6e4a7e8c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amqwanji'j/amqwanji'j.html", "entry_url": "https://mikmaqonline.org/entries/a/amqwanji'j/amqwanji'j.html", "headword": "amqwanji'j", "example_index": 0, "raw_html_path": "raw/entries/52087b89c11b1163f77306624a3afb896ceb06b2122c8571ba53494be79d8a66.html", "raw_html_sha256": "a9ce2d3f70a0df34395dccc6e4116601c499a36bfb94cbd33191f748f57e1a25", "fetched_at": "2026-07-12T02:36:54.840Z", "recordings": [ { "recording_id": "11da5cd11e84a886847d8cc47a5e626a80c50427032d3ab61b7095399c1f33d5", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a77/a77176bb221ccabe30aa2b7a23d39214fe5b8d2ca89b25c68bf426a7f39f9f26.mp3", "archive_relative_path": "raw/audio/a77/a77176bb221ccabe30aa2b7a23d39214fe5b8d2ca89b25c68bf426a7f39f9f26.mp3" } ] } ], "prediction": "Ge' jugwa'toq aq gmu'j.", "reference": "P'tew aq amqwanji'j jugwa'tuwi." }, { "id": "mic-sent-1f4dd11cfd8fcbe1a7e8af96:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she bends down and laces up his/her shoe.", "output_text": "Waqjuiga'sit aq elaqpo'latl umugsnapi'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she bends down and laces up his/her shoe.", "mic_Latn": "Waqjuiga'sit aq elaqpo'latl umugsnapi'l." }, "canonical_ref": "entries/w/waqjuiga'sit/waqjuiga'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-638c5a3da22273b205b2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waqjuiga'sit/waqjuiga'sit.html", "entry_url": "https://mikmaqonline.org/entries/w/waqjuiga'sit/waqjuiga'sit.html", "headword": "waqjuiga'sit", "example_index": 0, "raw_html_path": "raw/entries/42f5010cb16b13bb406323496dc28248ec1a069917f4d3ee6f4509e60d4f5aaf.html", "raw_html_sha256": "53c37c090d8009d45c266fe58dde589dbea25b06b763193e7971ecb40c7258c5", "fetched_at": "2026-07-12T02:46:40.645Z", "recordings": [ { "recording_id": "3ee643973c5a46a99a751c94b1286eb1be1c8c9f1bae674987f85b0cd7042f10", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/621/621bea5eb6d144f8aada2d78dc1d32364bc95f674a87f5a5f7938df6164494bc.mp3", "archive_relative_path": "raw/audio/621/621bea5eb6d144f8aada2d78dc1d32364bc95f674a87f5a5f7938df6164494bc.mp3" } ] } ], "prediction": "Gesatg aq gesatg ugjit ugjit.", "reference": "Waqjuiga'sit aq elaqpo'latl umugsnapi'l." }, { "id": "mic-sent-1f5b8800aa2ca68a568d9756:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Many boards will be made from this tree.", "output_text": "Pugwelgig lasqo'plaq ugjietaq ula miti's.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Many boards will be made from this tree.", "mic_Latn": "Pugwelgig lasqo'plaq ugjietaq ula miti's." }, "canonical_ref": "entries/l/lasqo'plaw/lasqo'plaw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b1c3452363933285b968", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lasqo'plaw/lasqo'plaw.html", "entry_url": "https://mikmaqonline.org/entries/l/lasqo'plaw/lasqo'plaw.html", "headword": "lasqo'plaw", "example_index": 0, "raw_html_path": "raw/entries/ad18c48b3eb6cc48bfc0443bb9638791fb7c4a867d531c84ce8575179f700597.html", "raw_html_sha256": "2b40768e71d475d0cbb9d6ceb491d1a904671a8404bc8e0aa3cc3489be6579dc", "fetched_at": "2026-07-12T02:40:32.586Z", "recordings": [ { "recording_id": "61ec4fe7e7dbca52ad669a7d9fc447a58ef17a8315eb5e8775e2ad1ad930c569", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1d8/1d8154b0e559dcab789ec5f68c1c44d41adc166e7956d3ab9795a068384c8275.mp3", "archive_relative_path": "raw/audio/1d8/1d8154b0e559dcab789ec5f68c1c44d41adc166e7956d3ab9795a068384c8275.mp3" } ] } ], "prediction": "Pugwelga'toq ugjit na ula miti'g.", "reference": "Pugwelgig lasqo'plaq ugjietaq ula miti's." }, { "id": "mic-sent-1f8816007eddd643a67d325f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Peter challenges his older brother.", "output_text": "Pie'l wejignematl ugsisl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Peter challenges his older brother.", "mic_Latn": "Pie'l wejignematl ugsisl." }, "canonical_ref": "entries/w/wejignematl/wejignematl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-602e9a716190a1954ace", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejignematl/wejignematl.html", "entry_url": "https://mikmaqonline.org/entries/w/wejignematl/wejignematl.html", "headword": "wejignematl", "example_index": 0, "raw_html_path": "raw/entries/e01eb4bed6a5571d4caae69c301f254b4ad013973ba1287c575fa17c7e161daf.html", "raw_html_sha256": "198100f46370a93a3ccfffe71c6e3fde10997b66fdbeacce40193ccdf7150027", "fetched_at": "2026-07-12T02:46:52.720Z", "recordings": [ { "recording_id": "cbec5fc7bbe2774173573d75bb5d39290069342d921c9019ba3f0ef60283b921", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/04b/04b94ac2f2a98fd9bfa93a30be753591d867e1a8c6ccd38408bf81aa6070891c.mp3", "archive_relative_path": "raw/audio/04b/04b94ac2f2a98fd9bfa93a30be753591d867e1a8c6ccd38408bf81aa6070891c.mp3" } ] } ], "prediction": "Pie'l gesatg ugji'j.", "reference": "Pie'l wejignematl ugsisl." }, { "id": "mic-sent-1fc63ee93f7240047c213bdb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This ladder is tipsy.", "output_text": "Lgusuaqan menagwisg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This ladder is tipsy.", "mic_Latn": "Lgusuaqan menagwisg." }, "canonical_ref": "entries/m/menagwisg/menagwisg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-89ac4e8911dcc7be492a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/menagwisg/menagwisg.html", "entry_url": "https://mikmaqonline.org/entries/m/menagwisg/menagwisg.html", "headword": "menagwisg", "example_index": 0, "raw_html_path": "raw/entries/32141948b534457514a60ba2e70890da04e75e2c863cf9bea65ccc41dc002bc1.html", "raw_html_sha256": "1787faf5a4e4a06acb48f8403dd046ef6e0e88b2820aedea4664e5cd973c3d70", "fetched_at": "2026-07-12T02:41:13.786Z", "recordings": [ { "recording_id": "3fb91f5c702bb808f51de4bb1087f8be1211a2afd16831c9a3b5dc56b503a8cc", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d1b/d1bf68f1782c3f9e95a08d3e29b13dacb837c04354aeb8781d68d0cb2c7950a0.mp3", "archive_relative_path": "raw/audio/d1b/d1bf68f1782c3f9e95a08d3e29b13dacb837c04354aeb8781d68d0cb2c7950a0.mp3" } ] } ], "prediction": "We'gwi'g na ula gmu'j.", "reference": "Lgusuaqan menagwisg." }, { "id": "mic-sent-1ffdf388ea61e866d165ad57:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That little girl conceals her candy in her hand, she's afraid that someone will take it.", "output_text": "Ala epite'ji'j sepuijjeng ugsuitism, jipatg ugsua'tugsin.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That little girl conceals her candy in her hand, she's afraid that someone will take it.", "mic_Latn": "Ala epite'ji'j sepuijjeng ugsuitism, jipatg ugsua'tugsin." }, "canonical_ref": "entries/s/sepuijjeng/sepuijjeng.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bf2c53558e17974f878a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sepuijjeng/sepuijjeng.html", "entry_url": "https://mikmaqonline.org/entries/s/sepuijjeng/sepuijjeng.html", "headword": "sepuijjeng", "example_index": 0, "raw_html_path": "raw/entries/d79f2d0a0595865f7a22805ee84c252c6987a941edef0be590be5730202dcfb3.html", "raw_html_sha256": "55744547c2888c9a547b0c52cda6b5beeaef3e6d9aaac5a3139792a9a512ea51", "fetched_at": "2026-07-12T02:44:50.193Z", "recordings": [ { "recording_id": "9bbb166e6b5329b2a2dfed4771ed2c6e23cb09fd0c6acdaa4fb32a7c3c6904bc", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fee/feee1e0347f94f3facd2aca45acd581c07a41e51198ffb5fbf57b0139725fc8a.mp3", "archive_relative_path": "raw/audio/fee/feee1e0347f94f3facd2aca45acd581c07a41e51198ffb5fbf57b0139725fc8a.mp3" } ] } ], "prediction": "E'pite'ji'j na gmu'j gesatg ugta'qann, tlia'tm na ji'nm goqwei.", "reference": "Ala epite'ji'j sepuijjeng ugsuitism, jipatg ugsua'tugsin." }, { "id": "mic-sent-201449099c77f882f6074760:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she was traveling on a horse when he/she left.", "output_text": "Te'sipowa'qapnaq maja'siteg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she was traveling on a horse when he/she left.", "mic_Latn": "Te'sipowa'qapnaq maja'siteg." }, "canonical_ref": "entries/t/te'sipowa'q/te'sipowa'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d6a23643f209f7a82edd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/te'sipowa'q/te'sipowa'q.html", "entry_url": "https://mikmaqonline.org/entries/t/te'sipowa'q/te'sipowa'q.html", "headword": "te'sipowa'q", "example_index": 0, "raw_html_path": "raw/entries/5a27c902761ee801fc84d388678c225880bbee733343e522d28a39fad2b027f8.html", "raw_html_sha256": "e3a61f3a9e98c73764e6a7b8c1b079076e32a52830930d498825187fba396123", "fetched_at": "2026-07-12T02:45:45.551Z", "recordings": [ { "recording_id": "374d0e5b7f8998bb83c9bf06f6df0665c0941a7632d10717048a433e4a622bb1", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/89b/89b589654ee92fa0eb579edbc90b791761c7fc61065e1cf177d2e2e16cfe6234.mp3", "archive_relative_path": "raw/audio/89b/89b589654ee92fa0eb579edbc90b791761c7fc61065e1cf177d2e2e16cfe6234.mp3" } ] } ], "prediction": "Nmu'ji'j gesatg ta'n tujiw wejiaq.", "reference": "Te'sipowa'qapnaq maja'siteg." }, { "id": "mic-sent-2029bbbfdaa83a9cddfce86a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I let my mother off at her house.", "output_text": "Gepta'l'g ngij wiguaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I let my mother off at her house.", "mic_Latn": "Gepta'l'g ngij wiguaq." }, "canonical_ref": "entries/g/gepta'latl/gepta'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c8911720c56315a7ab9b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gepta'latl/gepta'latl.html", "entry_url": "https://mikmaqonline.org/entries/g/gepta'latl/gepta'latl.html", "headword": "gepta'latl", "example_index": 0, "raw_html_path": "raw/entries/77ae8a349cd018278bb8ac2a23155170d3ab10aef2079631aabbeade8ec32872.html", "raw_html_sha256": "eb8f103b48c5935efd4d5fedd36b9c610225b645c4d195548cfe7d4bfaa9f59d", "fetched_at": "2026-07-12T02:39:01.292Z", "recordings": [ { "recording_id": "2e36e15787b447d27d2020daf09f51c107319def8267c8c1cd110fe8bfba7dce", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/545/545d560120d950991a2a81b9a96cc142ca6435126156a776058274be3064c27e.mp3", "archive_relative_path": "raw/audio/545/545d560120d950991a2a81b9a96cc142ca6435126156a776058274be3064c27e.mp3" } ] } ], "prediction": "Gi's nugu' ni'n eteg.", "reference": "Gepta'l'g ngij wiguaq." }, { "id": "mic-sent-2079c8d90f39eadaff9c7157:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she almost chopped his/her finger off because he/she was looking around.", "output_text": "Suel ugtluign temte'g ge's alapij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she almost chopped his/her finger off because he/she was looking around.", "mic_Latn": "Suel ugtluign temte'g ge's alapij." }, "canonical_ref": "entries/t/temte'g/temte'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8a3abcffb61ff83e1155", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/temte'g/temte'g.html", "entry_url": "https://mikmaqonline.org/entries/t/temte'g/temte'g.html", "headword": "temte'g", "example_index": 0, "raw_html_path": "raw/entries/6650073d0e8f0360b9d79128065baa27cdfdd7ce703cdf1b4b495b00982711d7.html", "raw_html_sha256": "980352ab00d54e1b4ab3626528ef9723cd1c1ef7e412e267aef0f38296a9173d", "fetched_at": "2026-07-12T02:45:39.830Z", "recordings": [ { "recording_id": "eb0dacfc037f9a56c73460920b03002d9b54e955c6892c59b9092666596c6e97", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/99a/99afd1642a65cc2f9f2fd02363e5e6e864a57ae018ab46c9a820947578e5ef2a.mp3", "archive_relative_path": "raw/audio/99a/99afd1642a65cc2f9f2fd02363e5e6e864a57ae018ab46c9a820947578e5ef2a.mp3" } ] } ], "prediction": "Gaqama'toq ugta'latl ugti'l muta gisgugwet.", "reference": "Suel ugtluign temte'g ge's alapij." }, { "id": "mic-sent-21262e983d1681feb7c70406:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she got stuck between those trees.", "output_text": "Etliamjimoqiep ala pitui'w miti'sg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she got stuck between those trees.", "mic_Latn": "Etliamjimoqiep ala pitui'w miti'sg." }, "canonical_ref": "entries/p/pitui'w/pitui'w.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5f487f48d355403e62f6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pitui'w/pitui'w.html", "entry_url": "https://mikmaqonline.org/entries/p/pitui'w/pitui'w.html", "headword": "pitui'w", "example_index": 0, "raw_html_path": "raw/entries/edaef5c5e6663c1302c8e9c4dfc7d5aa718c6165bb6cffbaa42d40008c05a9bb.html", "raw_html_sha256": "38871589f0392e5e8d0ae31e7068396afda2d861701245e9ba44746115dac92e", "fetched_at": "2026-07-12T02:44:10.410Z", "recordings": [ { "recording_id": "161fb6da48ec6794d840fb5a05fcf62f9f41d862a577a9717480718299bf596d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/46d/46d50bb3fa25fba0d4e87f376b4db5761f75e4976b4c3fc99de8dcdd71be5a24.mp3", "archive_relative_path": "raw/audio/46d/46d50bb3fa25fba0d4e87f376b4db5761f75e4976b4c3fc99de8dcdd71be5a24.mp3" } ] } ], "prediction": "Gesatg na miti's.", "reference": "Etliamjimoqiep ala pitui'w miti'sg." }, { "id": "mic-sent-2136b328d8be59cdc5309afd:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she tries to go fast, but can't help it, he/she goes along slowly.", "output_text": "Wejo'tg gsigawa'sin, gatu ejela'toq, pemigegwi'pit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she tries to go fast, but can't help it, he/she goes along slowly.", "mic_Latn": "Wejo'tg gsigawa'sin, gatu ejela'toq, pemigegwi'pit." }, "canonical_ref": "entries/p/pemigegwi'pit/pemigegwi'pit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c8e35fa0d9721741b482", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemigegwi'pit/pemigegwi'pit.html", "entry_url": "https://mikmaqonline.org/entries/p/pemigegwi'pit/pemigegwi'pit.html", "headword": "pemigegwi'pit", "example_index": 0, "raw_html_path": "raw/entries/5e22f2d37f2d72718827bd6d1dd2a2ccc48f98b94c4091e6f80361a8f4fe6575.html", "raw_html_sha256": "a17a29c3c341c94dbc39bf7e216f927847cb164d4128d43e3c0efc0ff6ad03cc", "fetched_at": "2026-07-12T02:43:31.594Z", "recordings": [ { "recording_id": "756de94c291b9ebbdbd2ecc67addddce936934e541d71963144f98e1937a328b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/54d/54d1a65f4d2aa417d4b69ece99d22901e6489831f285f8537fb6a2b4769987a1.mp3", "archive_relative_path": "raw/audio/54d/54d1a65f4d2aa417d4b69ece99d22901e6489831f285f8537fb6a2b4769987a1.mp3" } ] } ], "prediction": "Pugwelg, gatu mu gesatg, maljewe'g.", "reference": "Wejo'tg gsigawa'sin, gatu ejela'toq, pemigegwi'pit." }, { "id": "mic-sent-21a66e2396065ea5ddc95122:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Take it easy my friend!", "output_text": "Unjaqajewa'tegetes nitap!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Take it easy my friend!", "mic_Latn": "Unjaqajewa'tegetes nitap!" }, "canonical_ref": "entries/u/unjaqajewa'teget/unjaqajewa'teget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2156b64cd709789d267b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/unjaqajewa'teget/unjaqajewa'teget.html", "entry_url": "https://mikmaqonline.org/entries/u/unjaqajewa'teget/unjaqajewa'teget.html", "headword": "unjaqajewa'teget", "example_index": 0, "raw_html_path": "raw/entries/c9c0d63a58ea46585c2335eb70f8ab70e4dfa0570ada9e296db79d3c138c53c2.html", "raw_html_sha256": "395210c5432efc315e147c2949bb6744aa278051d555a3e885d19830dac48191", "fetched_at": "2026-07-12T02:46:25.860Z", "recordings": [ { "recording_id": "6a9742969236c390924162dc684e83d983d7f65b083156578ea8427189fd6cb9", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d7a/d7a5abca71976ea28e32a6853b37b658083fe5d1869fb7afe5591206cf658135.mp3", "archive_relative_path": "raw/audio/d7a/d7a5abca71976ea28e32a6853b37b658083fe5d1869fb7afe5591206cf658135.mp3" } ] } ], "prediction": "Gi's na nitap!", "reference": "Unjaqajewa'tegetes nitap!" }, { "id": "mic-sent-21b5daadea242b713bd7daa1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's hard to make a quill work basket.", "output_text": "Mawimtue'g ligpenigen gawiei eltmg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's hard to make a quill work basket.", "mic_Latn": "Mawimtue'g ligpenigen gawiei eltmg." }, "canonical_ref": "entries/g/gawiei/gawiei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c751755712bc172c4c90", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gawiei/gawiei.html", "entry_url": "https://mikmaqonline.org/entries/g/gawiei/gawiei.html", "headword": "gawiei", "example_index": 0, "raw_html_path": "raw/entries/31833cc75cd280e1d57c233e05a9ab8396e68789d2e9db5a101497681e911d00.html", "raw_html_sha256": "8b2c0af582c740e36d6999888a1c4df2123424e506cf41f95fa308e457db7266", "fetched_at": "2026-07-12T02:38:47.334Z", "recordings": [ { "recording_id": "789daf96fcc4c6206ae1cfa1c5b45ff6781ec8995ad4f98485f1803fd5f0ddc7", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a4f/a4facf22a66135dc59c9f2a12395e0d7de8b7c50529198c8c2f2cbdcc0784513.mp3", "archive_relative_path": "raw/audio/a4f/a4facf22a66135dc59c9f2a12395e0d7de8b7c50529198c8c2f2cbdcc0784513.mp3" } ] } ], "prediction": "We'gwi'g ta'n tujiw gmu'j.", "reference": "Mawimtue'g ligpenigen gawiei eltmg." }, { "id": "mic-sent-21de158309096fe02f49788f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Wear a good shirt.", "output_text": "Nasgu gelu'sit atla'i.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Wear a good shirt.", "mic_Latn": "Nasgu gelu'sit atla'i." }, "canonical_ref": "entries/g/gelu'sit/gelu'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-95ac5fdb6244c58f4386", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gelu'sit/gelu'sit.html", "entry_url": "https://mikmaqonline.org/entries/g/gelu'sit/gelu'sit.html", "headword": "gelu'sit", "example_index": 0, "raw_html_path": "raw/entries/1cad71852241c3f2baf1d613809078da11c2e73c1378b1f81d7ebf137f504da7.html", "raw_html_sha256": "b10461e2fa029005c6de3c615a5c5751d49eba80fd46802356a075097edbfdad", "fetched_at": "2026-07-12T02:38:57.588Z", "recordings": [ { "recording_id": "e57ca7cf7c436d8ffdbdaa82667ee4d24874796145fac3a3ed2f28324511574e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1b8/1b82dab918214e0b65ad7fd7175b2523b852c775f0e20c1bc484046282a670e8.mp3", "archive_relative_path": "raw/audio/1b8/1b82dab918214e0b65ad7fd7175b2523b852c775f0e20c1bc484046282a670e8.mp3" } ] } ], "prediction": "Pugwelga'toq ga'qan.", "reference": "Nasgu gelu'sit atla'i." }, { "id": "mic-sent-21f8ac50bb7e6fa7a8da13bb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "How far does this wire go?", "output_text": "Tal gneg eltaqaiaq ula qasawo'qapi?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "How far does this wire go?", "mic_Latn": "Tal gneg eltaqaiaq ula qasawo'qapi?" }, "canonical_ref": "entries/e/eltaqaiaq/eltaqaiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-68e9b8602574d5ae0cbc", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/eltaqaiaq/eltaqaiaq.html", "entry_url": "https://mikmaqonline.org/entries/e/eltaqaiaq/eltaqaiaq.html", "headword": "eltaqaiaq", "example_index": 0, "raw_html_path": "raw/entries/98d3301b6c2a01e4a4f7e6f5f69607838f43749f44b14af8c7220d403f87effa.html", "raw_html_sha256": "8bad786600dac791d639361cb936b10a481bfb4fb8e1518d9e189baac6c9ef68", "fetched_at": "2026-07-12T02:37:52.332Z", "recordings": [ { "recording_id": "102d0c4b55da50f20a767b768a9999996042e9c066c28636c83560a03df05c90", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ec5/ec50fd1c47ed7a6b48c4d5fd9b127a986f8e3788b62142ff24d2a34548dd3968.mp3", "archive_relative_path": "raw/audio/ec5/ec50fd1c47ed7a6b48c4d5fd9b127a986f8e3788b62142ff24d2a34548dd3968.mp3" } ] } ], "prediction": "Ta'sijig ula gmu'j?", "reference": "Tal gneg eltaqaiaq ula qasawo'qapi?" }, { "id": "mic-sent-21fe35f6b55c3d464fedbe20:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My dog likes to lay on moose hide.", "output_text": "Nti gesatg enaqsij tia'muegn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My dog likes to lay on moose hide.", "mic_Latn": "Nti gesatg enaqsij tia'muegn." }, "canonical_ref": "entries/e/enaqsit/enaqsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ef06aa786f0a0a6069cb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/enaqsit/enaqsit.html", "entry_url": "https://mikmaqonline.org/entries/e/enaqsit/enaqsit.html", "headword": "enaqsit", "example_index": 0, "raw_html_path": "raw/entries/2d29ac012ebebfc0f9288011f59e0608264867a374197ef3e3f429730a446ed5.html", "raw_html_sha256": "b55a8ee665018b16193b34b1845abe650eb4a370e2bbef5f834a70c89059f0f6", "fetched_at": "2026-07-12T02:37:59.565Z", "recordings": [ { "recording_id": "a453782beb8f475b9a8befe64fbb5069b971d361e760f92da0ade6d6943482eb", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1f2/1f23560c3c60fdf2d7a7c549e544ff9ff95eea037292d473e1f2da49a974ea61.mp3", "archive_relative_path": "raw/audio/1f2/1f23560c3c60fdf2d7a7c549e544ff9ff95eea037292d473e1f2da49a974ea61.mp3" } ] } ], "prediction": "Nmu'j gesgm'g na gmu'ji'j.", "reference": "Nti gesatg enaqsij tia'muegn." }, { "id": "mic-sent-22c6ff1f29673df243852fc2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I am the sitter whenever they leave.", "output_text": "Nujins'pi ta'n tujiw maita'tij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I am the sitter whenever they leave.", "mic_Latn": "Nujins'pi ta'n tujiw maita'tij." }, "canonical_ref": "entries/n/nujins'pit/nujins'pit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-705a85eb43839c3f61bc", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nujins'pit/nujins'pit.html", "entry_url": "https://mikmaqonline.org/entries/n/nujins'pit/nujins'pit.html", "headword": "nujins'pit", "example_index": 0, "raw_html_path": "raw/entries/c03b9ee162fcc4a63a8e0bc8d85e49a40ab948fd5c90b2d3f07f4d91817394ee.html", "raw_html_sha256": "dcf5d4019646571cd7907f54b99350c59d219c801a6a6775a0afe1fe69ca202e", "fetched_at": "2026-07-12T02:42:50.701Z", "recordings": [ { "recording_id": "93ed882d28d7791b4b473b635023ef8e6147cb622dd052976a5aeb2c1d7ce1e0", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/011/011aa0c98c56c559ed17976bed4caf9f8c73dd35c9581f990b60160e09641f34.mp3", "archive_relative_path": "raw/audio/011/011aa0c98c56c559ed17976bed4caf9f8c73dd35c9581f990b60160e09641f34.mp3" } ] } ], "prediction": "Ni'n na ni'n tujiw ta'n te's'g.", "reference": "Nujins'pi ta'n tujiw maita'tij." }, { "id": "mic-sent-22e617b1078c473866d9715e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It was gusty last night.", "output_text": "Weglams'geg wela'gwe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It was gusty last night.", "mic_Latn": "Weglams'geg wela'gwe'g." }, "canonical_ref": "entries/w/weglams'g/weglams'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-52501b1c1c05174501fa", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/weglams'g/weglams'g.html", "entry_url": "https://mikmaqonline.org/entries/w/weglams'g/weglams'g.html", "headword": "weglams'g", "example_index": 0, "raw_html_path": "raw/entries/14166eda97b020701ac6b99c7f9803bfaa89488d4b67d37952dbaf7867e1f6e3.html", "raw_html_sha256": "6e23957bbdb40f528231e1bcdafeaf0817c5af0fc097604923de5df2f7baf042", "fetched_at": "2026-07-12T02:46:45.688Z", "recordings": [ { "recording_id": "fb37f8f33f2bf7c24015c5923993073589cca8cac4242f8b6f3da4ad10fcd47b", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/632/63233b8edc8322fef68cf790f4a1c32c5675470eba1bf66cbb3f77a0b37fcd0a.mp3", "archive_relative_path": "raw/audio/632/63233b8edc8322fef68cf790f4a1c32c5675470eba1bf66cbb3f77a0b37fcd0a.mp3" } ] } ], "prediction": "Wela'gwe'g gisgug.", "reference": "Weglams'geg wela'gwe'g." }, { "id": "mic-sent-230fd1758b97f6f3c7ae7700:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My daughter is being a daughter-in-law in Gesgapegiaq.", "output_text": "Ntus etllu'sugwe'sgewit Gesgapegiaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My daughter is being a daughter-in-law in Gesgapegiaq.", "mic_Latn": "Ntus etllu'sugwe'sgewit Gesgapegiaq." }, "canonical_ref": "entries/l/lu'sue'sgwewit/lu'sue'sgwewit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-50a3fe7c90d651807804", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lu'sue'sgwewit/lu'sue'sgwewit.html", "entry_url": "https://mikmaqonline.org/entries/l/lu'sue'sgwewit/lu'sue'sgwewit.html", "headword": "lu'sue'sgwewit", "example_index": 0, "raw_html_path": "raw/entries/bf119b1b09ebbf652547a93fcddb92a6e02c58834e7ff4521047b9f0e7cd4a11.html", "raw_html_sha256": "34855c11c3f769b1455cf58fd7c26ab1f5c7f6f9bd39cb1da10c82d29cddc5c1", "fetched_at": "2026-07-12T02:40:40.919Z", "recordings": [ { "recording_id": "a3490f1144b3c461bbba12262fb8d6d5cc5359b9667abd5258b685073f2aa1bb", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e1a/e1ada1758d7bfb6f9d7d0b9aa2444713a05fdae8065ea8136db3fb946bb098e9.mp3", "archive_relative_path": "raw/audio/e1a/e1ada1758d7bfb6f9d7d0b9aa2444713a05fdae8065ea8136db3fb946bb098e9.mp3" } ] } ], "prediction": "Ntus e'watm'g na Gesgapegiaq.", "reference": "Ntus etllu'sugwe'sgewit Gesgapegiaq." }, { "id": "mic-sent-23a82f691250524b638ceb44:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There are many Mi'gmaq who are soldiers.", "output_text": "Pugwelgig Mi'gmaq ta'n sma'gnisg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There are many Mi'gmaq who are soldiers.", "mic_Latn": "Pugwelgig Mi'gmaq ta'n sma'gnisg." }, "canonical_ref": "entries/s/sma'gnis/sma'gnis.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9e7dccc63cd9620b0807", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sma'gnis/sma'gnis.html", "entry_url": "https://mikmaqonline.org/entries/s/sma'gnis/sma'gnis.html", "headword": "sma'gnis", "example_index": 0, "raw_html_path": "raw/entries/6c329d1a6657f18ee16dd99685c061fc0e09d92969338bbf09219b5648050e41.html", "raw_html_sha256": "c05970b4619a003190b8f7c93640dc6fb1b269085da8d8e23148cf0ff1fe7cf5", "fetched_at": "2026-07-12T02:45:11.796Z", "recordings": [ { "recording_id": "6124369b7624696a07849ec39bd3966cdaed0e57439e73d318c0a3ef8392d1cd", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/356/356dcde70a523327069914001fd57153d5dd567bcd7d4a1679bc9a4791ba7b2c.mp3", "archive_relative_path": "raw/audio/356/356dcde70a523327069914001fd57153d5dd567bcd7d4a1679bc9a4791ba7b2c.mp3" } ] } ], "prediction": "Pugwelg Mi'gme'g na wi'gwi'jig.", "reference": "Pugwelgig Mi'gmaq ta'n sma'gnisg." }, { "id": "mic-sent-24b2593e88cde66ed510d845:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend takes good care of his/her grandmother.", "output_text": "Nitap weleiwatl ugumijl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend takes good care of his/her grandmother.", "mic_Latn": "Nitap weleiwatl ugumijl." }, "canonical_ref": "entries/w/weleiwatl/weleiwatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0e581b42c965b4e97317", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/weleiwatl/weleiwatl.html", "entry_url": "https://mikmaqonline.org/entries/w/weleiwatl/weleiwatl.html", "headword": "weleiwatl", "example_index": 0, "raw_html_path": "raw/entries/ab826df8a86c9e22b5b2443794055b04c210d93b67cec03f2f7877703c239dc5.html", "raw_html_sha256": "42689aff26bcfe1e2d68538c77bf6fa79dce191c8adaf93722c3128d0abd42a1", "fetched_at": "2026-07-12T02:46:59.663Z", "recordings": [ { "recording_id": "1a38c8c01e41a92993e8343ead62f0cb6539eee4e2d94d1fe761cb2125f04810", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/01c/01c384509f0a1a43db361b09dff9a1fc60c4bee757ebf63fab6ee851d6ea0c18.mp3", "archive_relative_path": "raw/audio/01c/01c384509f0a1a43db361b09dff9a1fc60c4bee757ebf63fab6ee851d6ea0c18.mp3" } ] } ], "prediction": "Ula nitap na ula nuji'j.", "reference": "Nitap weleiwatl ugumijl." }, { "id": "mic-sent-24cb9944492d9c03ab0632e1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I just singlehandedly paddled my canoe from up the mission.", "output_text": "Wane'g wetjigalugum ntul.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I just singlehandedly paddled my canoe from up the mission.", "mic_Latn": "Wane'g wetjigalugum ntul." }, "canonical_ref": "entries/j/jigalugg/jigalugg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-af6f89a42d2bcd4b7d34", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jigalugg/jigalugg.html", "entry_url": "https://mikmaqonline.org/entries/j/jigalugg/jigalugg.html", "headword": "jigalugg", "example_index": 0, "raw_html_path": "raw/entries/d4659f23a8f7f061f4e83d992d5acd33ff09c7a00fd2e71028627b6cc94d656d.html", "raw_html_sha256": "6592aed81d3a4a235823b5c7f57c3097c7ee1f84bd40cbd5e8a44ae23d03ee1d", "fetched_at": "2026-07-12T02:40:17.113Z", "recordings": [ { "recording_id": "d45a7ca9b600c479d735e1643f2e0059ef70e513be789a3c6a7833dd14074a29", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e51/e5179b854905193ec9b5e0bf7be83637620a0b6eeacc5ed1c2159d1b1b23cb8a.mp3", "archive_relative_path": "raw/audio/e51/e5179b854905193ec9b5e0bf7be83637620a0b6eeacc5ed1c2159d1b1b23cb8a.mp3" } ] } ], "prediction": "Pas'g pas'g na'te'g nugu' nmu'n gisipi'g.", "reference": "Wane'g wetjigalugum ntul." }, { "id": "mic-sent-253faccb8cf3e429606a2c15:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The ice here is thick enough, you can walk on it.", "output_text": "Tepiaq tetujipase'g ula mgumi, gisiusgijil'ga'tes.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The ice here is thick enough, you can walk on it.", "mic_Latn": "Tepiaq tetujipase'g ula mgumi, gisiusgijil'ga'tes." }, "canonical_ref": "entries/p/pase'g/pase'g.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b3450f0afa9d52078c2b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pase'g/pase'g.html", "entry_url": "https://mikmaqonline.org/entries/p/pase'g/pase'g.html", "headword": "pase'g", "example_index": 1, "raw_html_path": "raw/entries/e0304e44c89575e9a1eacaddba3ac1bf060b7baaadb0428ff1f231dce1719192.html", "raw_html_sha256": "6d4e184a28687c71d3c75b370b338cbe0056661a6c95cfe7c82899b3c2d77bcc", "fetched_at": "2026-07-12T02:43:13.423Z", "recordings": [ { "recording_id": "aaddb8e54b00fa4ebac7fda1e2da23330053f1a561ea74af0a9fea38a1830a79", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/91c/91c86222c7fd88b03e38b03461902be4ced7d798ef8a65a02191feeb65ec1702.mp3", "archive_relative_path": "raw/audio/91c/91c86222c7fd88b03e38b03461902be4ced7d798ef8a65a02191feeb65ec1702.mp3" } ] } ], "prediction": "Pilei gesatg ula gmu'ji'j, amujpa etl'g'p.", "reference": "Tepiaq tetujipase'g ula mgumi, gisiusgijil'ga'tes." }, { "id": "mic-sent-25718099bd5e761a248d8ff0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My garden is very uneven.", "output_text": "Ntiga'taqn we'gwimilqamigeg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My garden is very uneven.", "mic_Latn": "Ntiga'taqn we'gwimilqamigeg." }, "canonical_ref": "entries/m/milqamigeg/milqamigeg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-adef018f913ff3a9f9b3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/milqamigeg/milqamigeg.html", "entry_url": "https://mikmaqonline.org/entries/m/milqamigeg/milqamigeg.html", "headword": "milqamigeg", "example_index": 0, "raw_html_path": "raw/entries/17a837d0fd3cf39290a6578715e3ba4ccf0348f008a54200c50c3636db1a7cde.html", "raw_html_sha256": "9e05716f751b37851bf7895046bb22a06ec1551a510a7fcc6767a574d68839b4", "fetched_at": "2026-07-12T02:41:37.562Z", "recordings": [ { "recording_id": "721a93fa82f274835983acb3f41bcadad43d35fe5aa496c05b234b733c63d02f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2f2/2f240d163cec7cdc9ff6c8a6ee92f846dd30af194171dda4e49590b93eb2e150.mp3", "archive_relative_path": "raw/audio/2f2/2f240d163cec7cdc9ff6c8a6ee92f846dd30af194171dda4e49590b93eb2e150.mp3" } ] } ], "prediction": "Me' pugwelg na ntus.", "reference": "Ntiga'taqn we'gwimilqamigeg." }, { "id": "mic-sent-26098050e5a34d91ce5a4f90:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When we are playing cards is when we are really noisy.", "output_text": "Etllasgugutieg na maw sespoltieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When we are playing cards is when we are really noisy.", "mic_Latn": "Etllasgugutieg na maw sespoltieg." }, "canonical_ref": "entries/s/sespe'g/sespe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c972baec10ba56af87ae", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sespe'g/sespe'g.html", "entry_url": "https://mikmaqonline.org/entries/s/sespe'g/sespe'g.html", "headword": "sespe'g", "example_index": 0, "raw_html_path": "raw/entries/f6ac441ebf6bee56c7005652f16c350950da756bfb137b5df61d7f63be0b801a.html", "raw_html_sha256": "69c827399d3d4f05126bac8c3a7b23752785a5728a8a50bb302b2b73277d55c6", "fetched_at": "2026-07-12T02:44:52.506Z", "recordings": [ { "recording_id": "1f0ad8c0750354cc40e06e5005fdb94e0e04d60580fb40b36ad5037d96528cb4", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ee4/ee43f78e14dfe409789ca21ed0b2ea91642387ddf573bd6c28454e3ae44a78ad.mp3", "archive_relative_path": "raw/audio/ee4/ee43f78e14dfe409789ca21ed0b2ea91642387ddf573bd6c28454e3ae44a78ad.mp3" } ] } ], "prediction": "Ta'n tujiw jugwa'tujig ta'n te'sijig.", "reference": "Etllasgugutieg na maw sespoltieg." }, { "id": "mic-sent-263bf28f5889bb424ec66e0d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What is in your car?", "output_text": "Goqwei tepteg gutepaqang?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What is in your car?", "mic_Latn": "Goqwei tepteg gutepaqang?" }, "canonical_ref": "entries/t/tepteg/tepteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0c53f6bde653d7922c79", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tepteg/tepteg.html", "entry_url": "https://mikmaqonline.org/entries/t/tepteg/tepteg.html", "headword": "tepteg", "example_index": 0, "raw_html_path": "raw/entries/3a520bea35310a47050efbd9f5797849d563752ccad11512510b5bc0aee3f492.html", "raw_html_sha256": "934f1533d69d66e9bb877f638bd50612226d32bec550ad6132216fc07da259de", "fetched_at": "2026-07-12T02:45:44.948Z", "recordings": [ { "recording_id": "a25c918dfe3048917558cd990f8fcd02c746b0fc592e116a027b71c0f0e62bdd", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/820/8208021fa2f5a28feacd0c7afbeff2095783e1af5ead63563a0e048b53465125.mp3", "archive_relative_path": "raw/audio/820/8208021fa2f5a28feacd0c7afbeff2095783e1af5ead63563a0e048b53465125.mp3" } ] } ], "prediction": "Goqwei na utepaqan?", "reference": "Goqwei tepteg gutepaqang?" }, { "id": "mic-sent-268419a5838f0966689a179a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Take some handkerchiefs with you.", "output_text": "Musue'l ta's'gl nespne'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Take some handkerchiefs with you.", "mic_Latn": "Musue'l ta's'gl nespne'n." }, "canonical_ref": "entries/m/musuei/musuei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b1fcc7790badc37921c6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/musuei/musuei.html", "entry_url": "https://mikmaqonline.org/entries/m/musuei/musuei.html", "headword": "musuei", "example_index": 0, "raw_html_path": "raw/entries/8bae630d5b004afdf75ebee288ef79fcd1005ee3fb7d1f5f5e78fa673a42036f.html", "raw_html_sha256": "f4cdd95fe1ffa47437b79f080607a05433d194038c282517dda566e0f9441eeb", "fetched_at": "2026-07-12T02:41:53.253Z", "recordings": [ { "recording_id": "cb8619558be965f0b6b2d9604b351b57364e1ce80cc15de4ec291338eee8d465", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b61/b61006671fefb3ae136b82c48e3d34c4310087081d8a4ce79a2f4609be743a48.mp3", "archive_relative_path": "raw/audio/b61/b61006671fefb3ae136b82c48e3d34c4310087081d8a4ce79a2f4609be743a48.mp3" } ] } ], "prediction": "Pugwelg'g na gmu'ji'j.", "reference": "Musue'l ta's'gl nespne'n." }, { "id": "mic-sent-2704443579c39fa93eb3f96c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The hawthornberry bush is very prickely.", "output_text": "Go'gominaqsi'g maw ginigwejig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The hawthornberry bush is very prickely.", "mic_Latn": "Go'gominaqsi'g maw ginigwejig." }, "canonical_ref": "entries/g/go'gominaqsi/go'gominaqsi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-fed45189000706a0cf2e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/go'gominaqsi/go'gominaqsi.html", "entry_url": "https://mikmaqonline.org/entries/g/go'gominaqsi/go'gominaqsi.html", "headword": "go'gominaqsi", "example_index": 0, "raw_html_path": "raw/entries/ef5002a18401065866c6d91fe25c12c958b2b4b01db7c7d68fa7ca20ae2d910e.html", "raw_html_sha256": "7525a5e92e326f826090360e03ebd6c32f4994aab9a04391a7382262d9436503", "fetched_at": "2026-07-12T02:39:53.833Z", "recordings": [ { "recording_id": "9742a746a2ed6ff45cbf75cb6aa10f4d528a49049549f16dfc043f2ed06cacd5", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f8b/f8b306dd2703e220b5eb267d5214d738a44cd0a3d1560838e136973bb4c47744.mp3", "archive_relative_path": "raw/audio/f8b/f8b306dd2703e220b5eb267d5214d738a44cd0a3d1560838e136973bb4c47744.mp3" } ] } ], "prediction": "We'gwi'g na we'gwigtug.", "reference": "Go'gominaqsi'g maw ginigwejig." }, { "id": "mic-sent-2714db4fddf68a7ad0c74e44:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My mother and I are bringing the new quilt to a point.", "output_text": "Ni'n aq ngij sepusa'tueg pilei a'su'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My mother and I are bringing the new quilt to a point.", "mic_Latn": "Ni'n aq ngij sepusa'tueg pilei a'su'n." }, "canonical_ref": "entries/s/sepusa'toq/sepusa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ff35d4af33d0e5eb5380", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sepusa'toq/sepusa'toq.html", "entry_url": "https://mikmaqonline.org/entries/s/sepusa'toq/sepusa'toq.html", "headword": "sepusa'toq", "example_index": 0, "raw_html_path": "raw/entries/72fc795e30ff5402b40ab009f72168a4a655594af4f343eee79964332632e8fe.html", "raw_html_sha256": "f400ae8177869fb070e84584df114be1a92d6910288b004fa39f4b6aea6033f6", "fetched_at": "2026-07-12T02:44:50.499Z", "recordings": [ { "recording_id": "270f9554e16f5b1ab3f417bea4b85c38e7fa77399e24db6c3ecde56fc533e12f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a5e/a5e5d54768a88fd39f081f26bea6445e437ca2692bf5b22c3810c446b6702419.mp3", "archive_relative_path": "raw/audio/a5e/a5e5d54768a88fd39f081f26bea6445e437ca2692bf5b22c3810c446b6702419.mp3" } ] } ], "prediction": "Gi's aq nige' newte'g na pilei.", "reference": "Ni'n aq ngij sepusa'tueg pilei a'su'n." }, { "id": "mic-sent-27b8d818a72347b5981aeac9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary skunks her older sister.", "output_text": "Mali apigjilu'ta'tl umisl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary skunks her older sister.", "mic_Latn": "Mali apigjilu'ta'tl umisl." }, "canonical_ref": "entries/a/apigjilu'ta'tl/apigjilu'ta'tl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c2b15befd081565ff1fb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/apigjilu'ta'tl/apigjilu'ta'tl.html", "entry_url": "https://mikmaqonline.org/entries/a/apigjilu'ta'tl/apigjilu'ta'tl.html", "headword": "apigjilu'ta'tl", "example_index": 0, "raw_html_path": "raw/entries/7de6d22ab2f09d152a729947c552da651355e12d54d88626b76ef336e2b115e5.html", "raw_html_sha256": "3a1a1a402aa73b5eae97f3dfb2b1f24dd4013184bab66d4ae40e2b481b231ccd", "fetched_at": "2026-07-12T02:37:05.705Z", "recordings": [ { "recording_id": "5294f4a242ba6109acfa0eabb90eb46e534043314dc1e696abb1ba60ba94d034", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b92/b9220e349401554bbe5c90e80e720966a41381f7c64d587d18695d36bb693712.mp3", "archive_relative_path": "raw/audio/b92/b9220e349401554bbe5c90e80e720966a41381f7c64d587d18695d36bb693712.mp3" } ] } ], "prediction": "Mali gesatg ugjigtug.", "reference": "Mali apigjilu'ta'tl umisl." }, { "id": "mic-sent-27c02418b2f6ad3af88fa5dd:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My child is cross·eyed.", "output_text": "Nnjan patalapit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My child is cross·eyed.", "mic_Latn": "Nnjan patalapit." }, "canonical_ref": "entries/p/patalapit/patalapit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-422d8d75f06f4385872d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/patalapit/patalapit.html", "entry_url": "https://mikmaqonline.org/entries/p/patalapit/patalapit.html", "headword": "patalapit", "example_index": 0, "raw_html_path": "raw/entries/e93f86c6f59b2e69b18c0cbc24e7049b408625c66c905743fcc37fb7f9446414.html", "raw_html_sha256": "5d88aa0549c2e36d956a3a2a5758a512d2ef41bbdbdfdf4c5a8c4f1323a618fa", "fetched_at": "2026-07-12T02:43:17.232Z", "recordings": [ { "recording_id": "3164f1f685dea05caa21cfbc6735f4ab1d804e69b38fbc951d6d1d46d53af66f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/01e/01e4f7181e3d8a31645d112fffca685887912eb0d70fbf58d767e6b3f52bac17.mp3", "archive_relative_path": "raw/audio/01e/01e4f7181e3d8a31645d112fffca685887912eb0d70fbf58d767e6b3f52bac17.mp3" } ] } ], "prediction": "Ngwis na nitap.", "reference": "Nnjan patalapit." }, { "id": "mic-sent-27dd0e0b1e8a54236629d17d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Which one do you want, the red one or the navy blue one?", "output_text": "Tegen pewatmn, megwe'g gisna maqtawiewne'g?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Which one do you want, the red one or the navy blue one?", "mic_Latn": "Tegen pewatmn, megwe'g gisna maqtawiewne'g?" }, "canonical_ref": "entries/t/tegen/tegen.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-67e996705bb256bc7153", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tegen/tegen.html", "entry_url": "https://mikmaqonline.org/entries/t/tegen/tegen.html", "headword": "tegen", "example_index": 0, "raw_html_path": "raw/entries/de5da7ecfe3033d604c3d5f4e64c688ae98404df9ca0e1cf5705bc19331ed83c.html", "raw_html_sha256": "19934137219a1784755cf129d16be8df3a0a70a3a5178f645be5516763ae5245", "fetched_at": "2026-07-12T02:45:27.467Z", "recordings": [ { "recording_id": "175c9d63dbeb9c2b404a265630365822c1cecf477b249c5e31843c19d159647a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/06a/06a0bfa44c3b09a81d50adf07dc219d5f6dc86ca369263de035a20a4ce791345.mp3", "archive_relative_path": "raw/audio/06a/06a0bfa44c3b09a81d50adf07dc219d5f6dc86ca369263de035a20a4ce791345.mp3" } ] } ], "prediction": "Ta'n ta'n goqwei, lpa wijo'ji'jg aq lpa gmu'jig?", "reference": "Tegen pewatmn, megwe'g gisna maqtawiewne'g?" }, { "id": "mic-sent-285675d307777c9cae96d6c8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Is there any thing else?", "output_text": "Ap eta goqwei?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Is there any thing else?", "mic_Latn": "Ap eta goqwei?" }, "canonical_ref": "entries/e/eta/eta.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-65bfec82ca7c6e1566e6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/eta/eta.html", "entry_url": "https://mikmaqonline.org/entries/e/eta/eta.html", "headword": "eta", "example_index": 1, "raw_html_path": "raw/entries/537e97511fbb77626365e30b6f7dd183395312a6a82cfc8166f2f61262e7cea7.html", "raw_html_sha256": "7b925ecdd61dd2f31de1fc7c2bc5b5b68a4c60cd346328079991cef1531ea99e", "fetched_at": "2026-07-12T02:38:20.973Z", "recordings": [ { "recording_id": "0df89360b9d9091c3ff8f944e75989bbdd0f9086172043c0e6b1115b6c38b97c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9cf/9cf8424a60a360bc85b06660003bde772cd716e7957c53969d752cbb3e6ed714.mp3", "archive_relative_path": "raw/audio/9cf/9cf8424a60a360bc85b06660003bde772cd716e7957c53969d752cbb3e6ed714.mp3" } ] } ], "prediction": "Me' newte'l ta'n goqwei?", "reference": "Ap eta goqwei?" }, { "id": "mic-sent-286f0768af73a5f789696af5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The fighter flattens the other fighter.", "output_text": "Matnaggewinu mesaqaneita'tl igtigl matnaggewinu'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The fighter flattens the other fighter.", "mic_Latn": "Matnaggewinu mesaqaneita'tl igtigl matnaggewinu'l." }, "canonical_ref": "entries/m/mesaqaneita'tl/mesaqaneita'tl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-57a77a9680f092a0efb1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mesaqaneita'tl/mesaqaneita'tl.html", "entry_url": "https://mikmaqonline.org/entries/m/mesaqaneita'tl/mesaqaneita'tl.html", "headword": "mesaqaneita'tl", "example_index": 0, "raw_html_path": "raw/entries/e496fba66fd31b6e06e98bc0b8f3e465a773b6cc8c8166c98b2a4defc35d63b5.html", "raw_html_sha256": "6996e432e146afa9f6cd88f1c0dbc6ae99c69668e5813b853f01d4e191171093", "fetched_at": "2026-07-12T02:41:19.216Z", "recordings": [ { "recording_id": "50bd92b0d9b00bd7424e885515afea9c5c39cdc287ad5cfb9535651259f9e743", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4f2/4f281ff22f20c8b6d3b6adf7f05aa2f2c21ff5a0a29d40bf3cd6bfb934b832f6.mp3", "archive_relative_path": "raw/audio/4f2/4f281ff22f20c8b6d3b6adf7f05aa2f2c21ff5a0a29d40bf3cd6bfb934b832f6.mp3" } ] } ], "prediction": "Lpa we'gwi'j gesatg ula we'gwigw.", "reference": "Matnaggewinu mesaqaneita'tl igtigl matnaggewinu'l." }, { "id": "mic-sent-292bb02d521941fab7fc0782:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I see a moose and he has large antlers.", "output_text": "Tia'm nemi'g aq mesgilnijig ugsmu'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I see a moose and he has large antlers.", "mic_Latn": "Tia'm nemi'g aq mesgilnijig ugsmu'g." }, "canonical_ref": "entries/u/ugsmu'l/ugsmu'l.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-77c35a941fb61c618b53", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugsmu'l/ugsmu'l.html", "entry_url": "https://mikmaqonline.org/entries/u/ugsmu'l/ugsmu'l.html", "headword": "ugsmu'l", "example_index": 0, "raw_html_path": "raw/entries/4dabd7497bb87a03a6dcb0380de64fc0e99787e62ed2f432e8cb6bef732fbe59.html", "raw_html_sha256": "9e17da9b6187a5483d8ae857cca372e68297835715563aa6ab7130518db7fb40", "fetched_at": "2026-07-12T02:46:15.835Z", "recordings": [ { "recording_id": "b1c9810897c091011c772254588d649749cabd1dc744eb8798de0e786f303399", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b64/b64e64ea58bad1e62227e8df3a0c6b37f0707f0d988c2ccc5c6a823ba49516fa.mp3", "archive_relative_path": "raw/audio/b64/b64e64ea58bad1e62227e8df3a0c6b37f0707f0d988c2ccc5c6a823ba49516fa.mp3" } ] } ], "prediction": "Amujpa'q na ni'n aq gesgm'g.", "reference": "Tia'm nemi'g aq mesgilnijig ugsmu'g." }, { "id": "mic-sent-296336aea654dde56a3655cf:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What kind of medicine do you take?", "output_text": "Talamu'g wesua'tu'n npisun?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What kind of medicine do you take?", "mic_Latn": "Talamu'g wesua'tu'n npisun?" }, "canonical_ref": "entries/n/npisun/npisun.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-58d89926fa4435332142", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/npisun/npisun.html", "entry_url": "https://mikmaqonline.org/entries/n/npisun/npisun.html", "headword": "npisun", "example_index": 0, "raw_html_path": "raw/entries/773a046c9c9ee8d1935c2064e43d3febcb4533dbad6bd01530801001de7887cc.html", "raw_html_sha256": "3dc2d2798d8cd651996f74f7bc11738ba24efd433d82d115b979694063c9488b", "fetched_at": "2026-07-12T02:42:42.361Z", "recordings": [ { "recording_id": "f45e492f69eb741c852afe008146122db2d6dd4b76ba4d62a61cad4a80c45f6b", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a5e/a5e421a66cc7fdabadc5798d5e6a431ed53a8ecff029f7304ca6bf8c65b5fb3d.mp3", "archive_relative_path": "raw/audio/a5e/a5e421a66cc7fdabadc5798d5e6a431ed53a8ecff029f7304ca6bf8c65b5fb3d.mp3" } ] } ], "prediction": "Ta's'g ta'n goqwei ugjit?", "reference": "Talamu'g wesua'tu'n npisun?" }, { "id": "mic-sent-29f1f304cc7eb695ca2e975d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That boat of yours is only half full.", "output_text": "Aqatamgiaq pas'g na gtul.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That boat of yours is only half full.", "mic_Latn": "Aqatamgiaq pas'g na gtul." }, "canonical_ref": "entries/a/aqtamgiaq/aqtamgiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6b57e0e47a35c2ec59c8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/aqtamgiaq/aqtamgiaq.html", "entry_url": "https://mikmaqonline.org/entries/a/aqtamgiaq/aqtamgiaq.html", "headword": "aqtamgiaq", "example_index": 0, "raw_html_path": "raw/entries/730bc7f35b4ae67552bc2bf8dbf9d8136b4c957686e4ca3c92ef46c069886948.html", "raw_html_sha256": "6abc15fe4d1ba33dc0c261762dd587709134893d884d2ab7def2bc0df2458e53", "fetched_at": "2026-07-12T02:37:17.269Z", "recordings": [ { "recording_id": "d2c27772ec1609a278bba08e58d908e0b328f1d4eed48a71a26e0d9209cb6cfa", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/aa8/aa862ca4d9e23b2459abaf6dd9eec312ec4d161cebcb66ff301837cbab2fac94.mp3", "archive_relative_path": "raw/audio/aa8/aa862ca4d9e23b2459abaf6dd9eec312ec4d161cebcb66ff301837cbab2fac94.mp3" } ] } ], "prediction": "Pas'g pas'g glapis'g na wi'gatign.", "reference": "Aqatamgiaq pas'g na gtul." }, { "id": "mic-sent-2ae447ee99169d5f191679e0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This pie is so sweet.", "output_text": "Na we'giseggw ula petaqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This pie is so sweet.", "mic_Latn": "Na we'giseggw ula petaqan." }, "canonical_ref": "entries/s/seggw/seggw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7bfa4d62f22832652e27", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/seggw/seggw.html", "entry_url": "https://mikmaqonline.org/entries/s/seggw/seggw.html", "headword": "seggw", "example_index": 0, "raw_html_path": "raw/entries/fe8a4ea07737eba6d9c561c1818b709f085bacba5cee0ef69a682e49ea544342.html", "raw_html_sha256": "d94813acd41b1a55332979f3820742a1761aecc800a5fae700ef9879fa485cbc", "fetched_at": "2026-07-12T02:44:48.083Z", "recordings": [ { "recording_id": "c18b82374b4fd71fbb85cd8ade00be3f0914ef8cd34a98d04003158497858c1f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/898/89855b4668c4f26ad7c09ff82da0242a0d9f2da81ebadc7526e6bc876db68c26.mp3", "archive_relative_path": "raw/audio/898/89855b4668c4f26ad7c09ff82da0242a0d9f2da81ebadc7526e6bc876db68c26.mp3" } ] } ], "prediction": "Telte'g na ula pi'g.", "reference": "Na we'giseggw ula petaqan." }, { "id": "mic-sent-2b4f9993fda58166d988ef1c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has to mend his/her boat because it leaks to much.", "output_text": "Amujpa nugu' mesna'toq ugtul muta wesams'peg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has to mend his/her boat because it leaks to much.", "mic_Latn": "Amujpa nugu' mesna'toq ugtul muta wesams'peg." }, "canonical_ref": "entries/m/mesna'toq/mesna'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-868cac3a7a8ca2a099d5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mesna'toq/mesna'toq.html", "entry_url": "https://mikmaqonline.org/entries/m/mesna'toq/mesna'toq.html", "headword": "mesna'toq", "example_index": 0, "raw_html_path": "raw/entries/f00c47f2ba9bb014b7050c4fded5070e015fc080fb80f59000122d17949c2119.html", "raw_html_sha256": "5b0dea20c19664f05ca3abdbcf9ea785916570007f2ec7393243ac2e9632dce1", "fetched_at": "2026-07-12T02:41:21.928Z", "recordings": [ { "recording_id": "aaee78867c4997d186a6f1995699dfc1810f13b264efcc64b25a65bafb55e2de", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3a5/3a56245918bf18c62d17b3cc764e13c80c7a2216e5f55039a016fc5668981463.mp3", "archive_relative_path": "raw/audio/3a5/3a56245918bf18c62d17b3cc764e13c80c7a2216e5f55039a016fc5668981463.mp3" } ] } ], "prediction": "Amujpa amujpa'toq ugjit muta ms't goqwei.", "reference": "Amujpa nugu' mesna'toq ugtul muta wesams'peg." }, { "id": "mic-sent-2bd029d0b2a8503e7a77c77d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I think s\\he luged his\\her in food for the week.", "output_text": "Etug petuptoq wilu ugjit aqantie'uti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I think s\\he luged his\\her in food for the week.", "mic_Latn": "Etug petuptoq wilu ugjit aqantie'uti." }, "canonical_ref": "entries/p/petuptoq/petuptoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-db282df18ab242bea9ef", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/petuptoq/petuptoq.html", "entry_url": "https://mikmaqonline.org/entries/p/petuptoq/petuptoq.html", "headword": "petuptoq", "example_index": 0, "raw_html_path": "raw/entries/7329bc5d6eb77f2ce60ae783ef0ab703f1c99f7b3b45051da4d2498acfc3c802.html", "raw_html_sha256": "aacdfc07024f42d9a8a9d4774fb5d13aaec42e5333ad43b4554ba5664c4bf129", "fetched_at": "2026-07-12T02:43:49.692Z", "recordings": [ { "recording_id": "1d17d352025611d06899f475ce88e1b7815cbf6e9347a6e48d3bc43326614418", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ef1/ef1709d218e1700c7107ed5a2c6bfe61194c1ac990778792072a414587547a80.mp3", "archive_relative_path": "raw/audio/ef1/ef1709d218e1700c7107ed5a2c6bfe61194c1ac990778792072a414587547a80.mp3" } ] } ], "prediction": "Telte'lma'toq ugjit ugta's'g ugjit.", "reference": "Etug petuptoq wilu ugjit aqantie'uti." }, { "id": "mic-sent-2c752ab0224a1ed6c864b550:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Tomorrow morning we are going to Montreal.", "output_text": "Egsitpu'nug Muliang eltaieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Tomorrow morning we are going to Montreal.", "mic_Latn": "Egsitpu'nug Muliang eltaieg." }, "canonical_ref": "entries/m/Mulian/Mulian.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c1a5e0d74894c161dd0d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/Mulian/Mulian.html", "entry_url": "https://mikmaqonline.org/entries/m/Mulian/Mulian.html", "headword": "Mulian", "example_index": 0, "raw_html_path": "raw/entries/b398c33ccfa15f8d2dbc81cc0157981dc7b60ab4c755bd495f7b0d20bc19e1ca.html", "raw_html_sha256": "39ab5db7ace0afd1edd39506c20e18d237b0a26054f77c6e980e7b26cf0524cd", "fetched_at": "2026-07-12T02:41:48.242Z", "recordings": [ { "recording_id": "ca1ecdd9bc5babdacf6c3bf5566dde9cff39abee125d951079d69423c216cca1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1b5/1b537f315f402f6e0244287c7719816e1e8e2d4aa76e2e29f4b50771539d5c57.mp3", "archive_relative_path": "raw/audio/1b5/1b537f315f402f6e0244287c7719816e1e8e2d4aa76e2e29f4b50771539d5c57.mp3" } ] } ], "prediction": "Sapo'siegsitpu'g na'te'l Munlie'l.", "reference": "Egsitpu'nug Muliang eltaieg." }, { "id": "mic-sent-2cb4babcda8dc09a6a6fa61a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When a salmon goes to spawn it must first swim up stream.", "output_text": "Ta'n tujiw plamu getu' siga'lat amujpa tmg toqjua't sipug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When a salmon goes to spawn it must first swim up stream.", "mic_Latn": "Ta'n tujiw plamu getu' siga'lat amujpa tmg toqjua't sipug." }, "canonical_ref": "entries/t/toqjua't/toqjua't.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-47e319729b41f2addac8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/toqjua't/toqjua't.html", "entry_url": "https://mikmaqonline.org/entries/t/toqjua't/toqjua't.html", "headword": "toqjua't", "example_index": 1, "raw_html_path": "raw/entries/0c3411b228bd72b140b7de9a260d502bc80f2f41c3a3efd1b7c03ff7fcece5da.html", "raw_html_sha256": "8fd6319b2e1d6065ecaa7a8f57f01aef73d5cc7873ccbf6923f7eb1c2c7d7214", "fetched_at": "2026-07-12T02:46:01.847Z", "recordings": [ { "recording_id": "d22c8f411d91b26182bf5d68075cbfd73bb36f27299e8804dd705d73e815fb10", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a12/a12b7c3167283a77e8a7e003d9536892803c6006628df5906876bbbd93c9d4a9.mp3", "archive_relative_path": "raw/audio/a12/a12b7c3167283a77e8a7e003d9536892803c6006628df5906876bbbd93c9d4a9.mp3" } ] } ], "prediction": "Ta'n tujiw plamu'g ta'n amujpa'toq gisijig.", "reference": "Ta'n tujiw plamu getu' siga'lat amujpa tmg toqjua't sipug." }, { "id": "mic-sent-2d2a4ed4b7e5db863f2959ff:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "His/her nostils are causing him/her pain.", "output_text": "Wittn asgaiatl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "His/her nostils are causing him/her pain.", "mic_Latn": "Wittn asgaiatl." }, "canonical_ref": "entries/w/witn/witn.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-79a0a93cf15b0ed3429f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/witn/witn.html", "entry_url": "https://mikmaqonline.org/entries/w/witn/witn.html", "headword": "witn", "example_index": 0, "raw_html_path": "raw/entries/9309d2566d4329786816e212fc7d8ff0cedc6ab13acb306ddb5570a715bf21a6.html", "raw_html_sha256": "76f04d8e3a5c6f557435d0fba999b22031973003a290033170074b55c00a967c", "fetched_at": "2026-07-12T02:47:41.962Z", "recordings": [ { "recording_id": "64f7848433939d14ae3442dee7c40fd07a420c25da205d8a5facfb90d7118494", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/084/084b9299fd1a57ec7fdc198f825efd7dc5e5af2282fd3d4d59c0c686f11180dd.mp3", "archive_relative_path": "raw/audio/084/084b9299fd1a57ec7fdc198f825efd7dc5e5af2282fd3d4d59c0c686f11180dd.mp3" } ] } ], "prediction": "Wela'g ugjit ugjit na ugjit.", "reference": "Wittn asgaiatl." }, { "id": "mic-sent-2d8a390e38033c9689fd629b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It didn't take him/her very long to go to the woods and back.", "output_text": "Naqs'tesg'g na ula nipugtug wejiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It didn't take him/her very long to go to the woods and back.", "mic_Latn": "Naqs'tesg'g na ula nipugtug wejiet." }, "canonical_ref": "entries/n/naqs'tesg'g/naqs'tesg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-03dd13c64017be2c9595", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/naqs'tesg'g/naqs'tesg'g.html", "entry_url": "https://mikmaqonline.org/entries/n/naqs'tesg'g/naqs'tesg'g.html", "headword": "naqs'tesg'g", "example_index": 0, "raw_html_path": "raw/entries/9aa1f245c8641c340582e2ddd57508f738c0a2157bbbd2c70655e628c0a060b8.html", "raw_html_sha256": "cbd09646e71cf6c022fac5c7a2981026da0a496e841d6c935a941d3cdb84ad27", "fetched_at": "2026-07-12T02:42:05.326Z", "recordings": [ { "recording_id": "2ce859a5cde0cf4de7e1693cae1217950d0494cb04009bb5115221b414c45048", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/99d/99dcd03530411b79e46ce4ba9a0d9ec95b765941d97f00e6c6de1a7e94641cdf.mp3", "archive_relative_path": "raw/audio/99d/99dcd03530411b79e46ce4ba9a0d9ec95b765941d97f00e6c6de1a7e94641cdf.mp3" } ] } ], "prediction": "Mu te's'g ta'n tujiw etlugsugwet.", "reference": "Naqs'tesg'g na ula nipugtug wejiet." }, { "id": "mic-sent-2da22bd075195f47941b5d00:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Really, sometimes I seem to be deaf!", "output_text": "Pana jijuaqa teleiasi gepistaqanai!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Really, sometimes I seem to be deaf!", "mic_Latn": "Pana jijuaqa teleiasi gepistaqanai!" }, "canonical_ref": "entries/g/gepistaqanat/gepistaqanat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2a2f0c594aba3ae31b41", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gepistaqanat/gepistaqanat.html", "entry_url": "https://mikmaqonline.org/entries/g/gepistaqanat/gepistaqanat.html", "headword": "gepistaqanat", "example_index": 0, "raw_html_path": "raw/entries/b0c3d6f94f17ef622d07adb0a0aed5decb3fe2a5c55258f201845753554b677b.html", "raw_html_sha256": "b9d0481c1a93961aac20432f8a7122c91578adbe5a36a4f87b9f11dbd7a71ea9", "fetched_at": "2026-07-12T02:38:59.278Z", "recordings": [ { "recording_id": "6ec9f40a9cbc67af827a2e4835392dcd397b157b9e4c509a15de976dd16db859", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/765/765aaee4dfb9552ea5d5206b88164f1bff304f057ef9c4a89c1d9fba5a26557c.mp3", "archive_relative_path": "raw/audio/765/765aaee4dfb9552ea5d5206b88164f1bff304f057ef9c4a89c1d9fba5a26557c.mp3" } ] } ], "prediction": "We'gwi'g, ta'n te'sij nige' negm!", "reference": "Pana jijuaqa teleiasi gepistaqanai!" }, { "id": "mic-sent-2db26066b3ac6c584f7996b3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "They are getting married at the church.", "output_text": "A's'tuo'guomg etlmalie'wijig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "They are getting married at the church.", "mic_Latn": "A's'tuo'guomg etlmalie'wijig." }, "canonical_ref": "entries/a/a's'tuo'guom/a's'tuo'guom.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9679ff29cbbf36f346d0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/a's'tuo'guom/a's'tuo'guom.html", "entry_url": "https://mikmaqonline.org/entries/a/a's'tuo'guom/a's'tuo'guom.html", "headword": "a's'tuo'guom", "example_index": 0, "raw_html_path": "raw/entries/62f7bb0d330c64f57e7c212731eaaaabab74cb0eebf0fa64012bcd1f62526852.html", "raw_html_sha256": "4597c4bb1f8d9f2bf16cd0f98bc53f3b143e8d80b5fa6f3e70201eb646bbf6f3", "fetched_at": "2026-07-12T02:37:22.635Z", "recordings": [ { "recording_id": "8867a3574577f93c4f73f141fc5609c1d0e93efaebd0654b0aeef7ed8ebe02ff", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c70/c70b4a98421a3a19c61d106b13500a01ee56b05273f7f45c16aa63340529a3d7.mp3", "archive_relative_path": "raw/audio/c70/c70b4a98421a3a19c61d106b13500a01ee56b05273f7f45c16aa63340529a3d7.mp3" } ] } ], "prediction": "Pugwelji'jig etlgwigtug.", "reference": "A's'tuo'guomg etlmalie'wijig." }, { "id": "mic-sent-2dbde9aaa8e73ee9a007bea9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My daughter had her jaw fixed.", "output_text": "Ntus ugtugwape'gn elugwatmutp.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My daughter had her jaw fixed.", "mic_Latn": "Ntus ugtugwape'gn elugwatmutp." }, "canonical_ref": "entries/u/ugtugwape'gn/ugtugwape'gn.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-54d4b5601ea2fc234e82", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugtugwape'gn/ugtugwape'gn.html", "entry_url": "https://mikmaqonline.org/entries/u/ugtugwape'gn/ugtugwape'gn.html", "headword": "ugtugwape'gn", "example_index": 0, "raw_html_path": "raw/entries/03118ff880b582af033e6c56456f55a36be86ffda7a55569264038440cb3e567.html", "raw_html_sha256": "6cfaedcfa0b1535e462f90daf793b8f57c31b6519b98e1bb9831932fe7a98d78", "fetched_at": "2026-07-12T02:46:19.329Z", "recordings": [ { "recording_id": "bf5878fbfad2e53091eef5d44bbb7d52c74e9500579daae6bcc33852afd9bb66", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a6d/a6d477b00dcf5b5358492a1856836f0ce6676040fa719ed7424a776795bebb53.mp3", "archive_relative_path": "raw/audio/a6d/a6d477b00dcf5b5358492a1856836f0ce6676040fa719ed7424a776795bebb53.mp3" } ] } ], "prediction": "Ntus gesatg ugjit ugjit.", "reference": "Ntus ugtugwape'gn elugwatmutp." }, { "id": "mic-sent-2deced44ada44eff3168821b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It is difficult to find a store that sells yards goods anymore.", "output_text": "Metua's'g nugu' magasan ta'n seiegn etlintuisgetas'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It is difficult to find a store that sells yards goods anymore.", "mic_Latn": "Metua's'g nugu' magasan ta'n seiegn etlintuisgetas'g." }, "canonical_ref": "entries/s/seiegn/seiegn.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f7a062b12d41db44da37", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/seiegn/seiegn.html", "entry_url": "https://mikmaqonline.org/entries/s/seiegn/seiegn.html", "headword": "seiegn", "example_index": 0, "raw_html_path": "raw/entries/f86ace4ef74cdd1fdb55d06ceb5fb9743578cfdd79fb1eb54585513daa743800.html", "raw_html_sha256": "70cfd379b9e1e7ebafc295e631adfb14fd790320b18608a3fd8f3db8808cd808", "fetched_at": "2026-07-12T02:44:48.469Z", "recordings": [ { "recording_id": "a77bad8c67b6d1e6edd67690c72d0e5f9ce05bac9a149a391478676c1598bb92", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f58/f5862e419c9420f2086b77b088d8d6125062ed83e5f15e978ff97f91a749023b.mp3", "archive_relative_path": "raw/audio/f58/f5862e419c9420f2086b77b088d8d6125062ed83e5f15e978ff97f91a749023b.mp3" } ] } ], "prediction": "Gi's gi's goqwei nugu' negm ta'n tujiw we'gwigtug.", "reference": "Metua's'g nugu' magasan ta'n seiegn etlintuisgetas'g." }, { "id": "mic-sent-2df5f638825981de22ceb687:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Peter takes his boat up river because he wants to go fishing tomorrow.", "output_text": "Pie'l pi'tawa'toq ugtul muta getu wesget sapo'nug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Peter takes his boat up river because he wants to go fishing tomorrow.", "mic_Latn": "Pie'l pi'tawa'toq ugtul muta getu wesget sapo'nug." }, "canonical_ref": "entries/p/pi'tawa'toq/pi'tawa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3826e6b13e4b8e429828", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pi'tawa'toq/pi'tawa'toq.html", "entry_url": "https://mikmaqonline.org/entries/p/pi'tawa'toq/pi'tawa'toq.html", "headword": "pi'tawa'toq", "example_index": 0, "raw_html_path": "raw/entries/169b6aa712e1d84bf298a07726fc3a807da0d112b7242fe216cb49b535168a0d.html", "raw_html_sha256": "ad9a21a71c34146af088004cf55fd6051badc1a12fe9a98330a7b2e1c3e91160", "fetched_at": "2026-07-12T02:44:07.101Z", "recordings": [ { "recording_id": "a20da6244c2c1683ec00690dd90fbd3655dd71f9ae92e11bb3da5b985c906625", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/31c/31c890c6a2a0383c42a16ee1f68606b89ae5304b3f2332959ce385bbf51815bb.mp3", "archive_relative_path": "raw/audio/31c/31c890c6a2a0383c42a16ee1f68606b89ae5304b3f2332959ce385bbf51815bb.mp3" } ] } ], "prediction": "Pie'l gesatg ugjit muta gisgug etlgwita'sit.", "reference": "Pie'l pi'tawa'toq ugtul muta getu wesget sapo'nug." }, { "id": "mic-sent-2e7c7d67b930d3c81b5a0469:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A scab is very sensative.", "output_text": "Ugjigi na mawnepe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A scab is very sensative.", "mic_Latn": "Ugjigi na mawnepe'g." }, "canonical_ref": "entries/u/ugjigi/ugjigi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-41aca05b6b62b3232558", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugjigi/ugjigi.html", "entry_url": "https://mikmaqonline.org/entries/u/ugjigi/ugjigi.html", "headword": "ugjigi", "example_index": 0, "raw_html_path": "raw/entries/ec1debffb31c9a1a586d945d5becc2ec80dde90b0caefc36e733fb59c7304461.html", "raw_html_sha256": "573bb0d627ee08f95b04ad64df008054b74523b305b6c4fd2f48b5a5a6e1d60d", "fetched_at": "2026-07-12T02:46:10.710Z", "recordings": [ { "recording_id": "5f96118c247b18973cdc4822af583af2d72fb6295f4ab460c8d1823e8ec644bf", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/739/73900ed8f3a877656876001b16ebaf6fc63d1ad5a658affb96696962f88a52c4.mp3", "archive_relative_path": "raw/audio/739/73900ed8f3a877656876001b16ebaf6fc63d1ad5a658affb96696962f88a52c4.mp3" } ] } ], "prediction": "Pugwelg na we'gwi'g.", "reference": "Ugjigi na mawnepe'g." }, { "id": "mic-sent-2f1f124ce62feb09fed5b607:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/She pays for supper.", "output_text": "Apangitg wela'gwewei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/She pays for supper.", "mic_Latn": "Apangitg wela'gwewei." }, "canonical_ref": "entries/a/apangitg/apangitg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f5feb361ce646ba28408", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/apangitg/apangitg.html", "entry_url": "https://mikmaqonline.org/entries/a/apangitg/apangitg.html", "headword": "apangitg", "example_index": 0, "raw_html_path": "raw/entries/6c037e3002d8d25c906e3c7ec24d5a7b6645a8400786068a80b5ae4c7dc1304d.html", "raw_html_sha256": "00da42c61d9164155edea00110705c776ca8074561e3a439af130e3d64bce712", "fetched_at": "2026-07-12T02:37:02.588Z", "recordings": [ { "recording_id": "ed034d7070750feafc597c4876b8630b9e1b65fbabc2d0d64b0ac7cc9ddee1be", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2c0/2c06540920823a495f844ff0995d5cc2d1c1f646b838f61d62e6f15b3f022a07.mp3", "archive_relative_path": "raw/audio/2c0/2c06540920823a495f844ff0995d5cc2d1c1f646b838f61d62e6f15b3f022a07.mp3" } ] } ], "prediction": "Pugwelg ugjit.", "reference": "Apangitg wela'gwewei." }, { "id": "mic-sent-2f52bae71aaea052ed5f7a7d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Many have married out from our community.", "output_text": "Pugwelg na gis tewmalie'wit ula gm'tginug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Many have married out from our community.", "mic_Latn": "Pugwelg na gis tewmalie'wit ula gm'tginug." }, "canonical_ref": "entries/t/tewmalie'wit/tewmalie'wit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a8cc304a9ee9e6eab263", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tewmalie'wit/tewmalie'wit.html", "entry_url": "https://mikmaqonline.org/entries/t/tewmalie'wit/tewmalie'wit.html", "headword": "tewmalie'wit", "example_index": 0, "raw_html_path": "raw/entries/c6882a412aaa39159fe9b2b4fc52450a3311500cf26e2c4bfb71561b222f75a4.html", "raw_html_sha256": "080897f5e6faefb78d332d7dec9235ab373a756cce1768842dc9312c58f8c5b4", "fetched_at": "2026-07-12T02:45:55.329Z", "recordings": [ { "recording_id": "47d38693beca1fce3d32ea55169cd9581249ac1a02a4665fa444a148005e8eee", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0e9/0e9c325ad88a6d90d48949d7ba230cf1e09f066ca82bf5f898bda21f0477fcd6.mp3", "archive_relative_path": "raw/audio/0e9/0e9c325ad88a6d90d48949d7ba230cf1e09f066ca82bf5f898bda21f0477fcd6.mp3" } ] } ], "prediction": "Ta'n te's'g gisi'gig ta'n tujiw.", "reference": "Pugwelg na gis tewmalie'wit ula gm'tginug." }, { "id": "mic-sent-2f7e6c4a565abcfbac32d509:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Daniel just doesn't want to stop pestering his brother.", "output_text": "Lpa Daniel mu getu'punajeiwagul ugjignaml.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Daniel just doesn't want to stop pestering his brother.", "mic_Latn": "Lpa Daniel mu getu'punajeiwagul ugjignaml." }, "canonical_ref": "entries/p/punajeiwatl/punajeiwatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f8faa4d99687ba2bf44d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/punajeiwatl/punajeiwatl.html", "entry_url": "https://mikmaqonline.org/entries/p/punajeiwatl/punajeiwatl.html", "headword": "punajeiwatl", "example_index": 0, "raw_html_path": "raw/entries/23feea800a1beebb949a93b4ec7813f795e80fcaf66d73a9bce4389c6941c6fc.html", "raw_html_sha256": "9c243a74cb927284133265b05306eba561801f0220509c79ca3511c6cc4a2323", "fetched_at": "2026-07-12T02:44:25.866Z", "recordings": [ { "recording_id": "609ad93564a795bf799a4a0393d0cab5d8e2ad3d5e26209644a9f384e6826061", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2b1/2b1564147f65701d2e3833cd954e507b05a6b5e4e6626d96c9b7130d4f472d0b.mp3", "archive_relative_path": "raw/audio/2b1/2b1564147f65701d2e3833cd954e507b05a6b5e4e6626d96c9b7130d4f472d0b.mp3" } ] } ], "prediction": "Ta'ne'l pas'g ma' nuta'tuatl ugjignaml.", "reference": "Lpa Daniel mu getu'punajeiwagul ugjignaml." }, { "id": "mic-sent-2f91555d4b19aaeec5111a5b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That constable is very friendly.", "output_text": "Ala gast'pl maw ni'laje'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That constable is very friendly.", "mic_Latn": "Ala gast'pl maw ni'laje'g." }, "canonical_ref": "entries/g/gast'pl/gast'pl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b58440b6d77f66e157d2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gast'pl/gast'pl.html", "entry_url": "https://mikmaqonline.org/entries/g/gast'pl/gast'pl.html", "headword": "gast'pl", "example_index": 0, "raw_html_path": "raw/entries/22856e71008b5a4dcb04048b8e73e691e84359d132db4410286f1fcc98d2c815.html", "raw_html_sha256": "a4bfbd304da1de85c0882997413d5d29bc1090b14b76733a4e2a246051638bf7", "fetched_at": "2026-07-12T02:38:45.020Z", "recordings": [ { "recording_id": "639307fbd58755ce3a7c90af93f442d16b546e08bd0d5bb0503e3699498e2d17", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c86/c86d85190ec2cd8aa0d8fffaf744090ab548a997addd8c4337e3e78a2e5d5700.mp3", "archive_relative_path": "raw/audio/c86/c86d85190ec2cd8aa0d8fffaf744090ab548a997addd8c4337e3e78a2e5d5700.mp3" } ] } ], "prediction": "We'gwi'g na wi'gatign.", "reference": "Ala gast'pl maw ni'laje'g." }, { "id": "mic-sent-2ff08a751b469d06df4ff294:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You will need many cut logs if you want to build a church.", "output_text": "Pugweltew jigata'sit tmoqte'gn nuta'n gtuitu'n als'tuo'guom. (Rerecord)", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You will need many cut logs if you want to build a church.", "mic_Latn": "Pugweltew jigata'sit tmoqte'gn nuta'n gtuitu'n als'tuo'guom. (Rerecord)" }, "canonical_ref": "entries/t/tmoqte_gn/tmoqte_gn.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f69ba52728a57b0806c0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tmoqte_gn/tmoqte_gn.html", "entry_url": "https://mikmaqonline.org/entries/t/tmoqte_gn/tmoqte_gn.html", "headword": "tmoqte’gn", "example_index": 0, "raw_html_path": "raw/entries/fa02d4c316fd41d6376e3dd4fd9215e2a4f38fff2a67e5a2e910437de8219c0d.html", "raw_html_sha256": "ece40ccd3d6d67a4582834172f77020647ee3854c522fa7a8c3aeaefb89bc3b8", "fetched_at": "2026-07-12T02:36:04.416Z", "recordings": [ { "recording_id": "b5a95a6d215dcb35ec819fb6320a367e4c7e722d91afcd3d75d491f8ce597236", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c1d/c1d39d5cec173922f19f52713e611af1fddb97c3e165bc82909d727ac16f4b78.mp3", "archive_relative_path": "raw/audio/c1d/c1d39d5cec173922f19f52713e611af1fddb97c3e165bc82909d727ac16f4b78.mp3" } ] } ], "prediction": "Pugwelg'p'tm'g ta'n tujiw gmu'j, ge' jugwa'sijig.", "reference": "Pugweltew jigata'sit tmoqte'gn nuta'n gtuitu'n als'tuo'guom. (Rerecord)" }, { "id": "mic-sent-303c5ab815512e2a71b15743:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The scythe is very handy for tall grass.", "output_text": "Psgweso'qon na mawuljewiaq ugjit pita'q msigu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The scythe is very handy for tall grass.", "mic_Latn": "Psgweso'qon na mawuljewiaq ugjit pita'q msigu." }, "canonical_ref": "entries/p/psgweso'qon/psgweso'qon.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0b74dac6e7e1b83c2398", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/psgweso'qon/psgweso'qon.html", "entry_url": "https://mikmaqonline.org/entries/p/psgweso'qon/psgweso'qon.html", "headword": "psgweso'qon", "example_index": 0, "raw_html_path": "raw/entries/72617271b882955bb55cc54cc50cd53c77831c2e8259ba0b3e9fb602d4dd856d.html", "raw_html_sha256": "431b4fc2c113d3b3701061e3f616917a15c10020b1587065af8cd2cae48f97f3", "fetched_at": "2026-07-12T02:44:19.457Z", "recordings": [ { "recording_id": "92d56a7a92d473b55908eb3f25d2327dae0883f3dd38ee942db6580c937bdfaa", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0e0/0e03ac04c025d9ebcece51879a09cd6a2e98f151e59b81673b0a5e2ddd8dd8f2.mp3", "archive_relative_path": "raw/audio/0e0/0e03ac04c025d9ebcece51879a09cd6a2e98f151e59b81673b0a5e2ddd8dd8f2.mp3" } ] } ], "prediction": "We'gwi'g na mawjiwji'jg ta'n tujiw gmu'jig.", "reference": "Psgweso'qon na mawuljewiaq ugjit pita'q msigu." }, { "id": "mic-sent-31ad47ca45a25793115f3f03:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Oh mother, my dress is ripped!", "output_text": "O' giju', temine'g ntmagotm!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Oh mother, my dress is ripped!", "mic_Latn": "O' giju', temine'g ntmagotm!" }, "canonical_ref": "entries/t/temine'g/temine'g.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-cfc1df8746e5280fe608", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/temine'g/temine'g.html", "entry_url": "https://mikmaqonline.org/entries/t/temine'g/temine'g.html", "headword": "temine'g", "example_index": 1, "raw_html_path": "raw/entries/2a8c85a24ffeb1d2bb6f530cd5146a2a0959c859719e386d337d1138c93553ef.html", "raw_html_sha256": "382159c06605c0c3f538e75f30c4fe6c2541ad21a9d5bdd8cd1ffacad1ac9815", "fetched_at": "2026-07-12T02:45:38.746Z", "recordings": [ { "recording_id": "a305040435410f73073dff31fe51f8a90594bcef8275991e5cb94f8fd01a558a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a34/a3428c9d8aca3a2a256391b87d58543e8b15839bed3cc7040e6643e9c9306e51.mp3", "archive_relative_path": "raw/audio/a34/a3428c9d8aca3a2a256391b87d58543e8b15839bed3cc7040e6643e9c9306e51.mp3" } ] } ], "prediction": "O'm, nugute'g ntpa'toq!", "reference": "O' giju', temine'g ntmagotm!" }, { "id": "mic-sent-320b31f16c11932dca1eff28:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she drops in every morning, for tea.", "output_text": "Peji'pit te'siegsitpu'g, najip'teweie'mat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she drops in every morning, for tea.", "mic_Latn": "Peji'pit te'siegsitpu'g, najip'teweie'mat." }, "canonical_ref": "entries/p/peji'pit/peji'pit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-64970f85db904e2a6215", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/peji'pit/peji'pit.html", "entry_url": "https://mikmaqonline.org/entries/p/peji'pit/peji'pit.html", "headword": "peji'pit", "example_index": 0, "raw_html_path": "raw/entries/f34855c84b96dd3166b815360a769361a2f8f953e267ece8db66f54afd10819a.html", "raw_html_sha256": "c81ef09455a9fabfc3c4b22fd2da48573775580123f4d595927c30d42735e41a", "fetched_at": "2026-07-12T02:43:24.968Z", "recordings": [ { "recording_id": "873b2b63ff7886e240680fdf1b03615b2d2bb1fa996ceb0118c41a0993ad07b3", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/679/6799f84513a9df632b4041606176b64a7b6f951f9422203385f9051bd1103010.mp3", "archive_relative_path": "raw/audio/679/6799f84513a9df632b4041606176b64a7b6f951f9422203385f9051bd1103010.mp3" } ] } ], "prediction": "Te'siegsitpu'g te'sipu'nug.", "reference": "Peji'pit te'siegsitpu'g, najip'teweie'mat." }, { "id": "mic-sent-32306e11329019658bca74dc:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "They row towards each other at the small lake.", "output_text": "Qospemji'jg etlia'sugwesugwijig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "They row towards each other at the small lake.", "mic_Latn": "Qospemji'jg etlia'sugwesugwijig." }, "canonical_ref": "entries/a/a'sugwesugwijig/a'sugwesugwijig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4291f2a8aa025d4d1775", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/a'sugwesugwijig/a'sugwesugwijig.html", "entry_url": "https://mikmaqonline.org/entries/a/a'sugwesugwijig/a'sugwesugwijig.html", "headword": "a'sugwesugwijig", "example_index": 0, "raw_html_path": "raw/entries/c9f81f77fe8409958022b9bce842de46655f00f85d4a023627957bcfd5544a28.html", "raw_html_sha256": "1a9921ae5912ffeb09e8217028ab0ca21a2d1a8575f426e526697b3efa643e0b", "fetched_at": "2026-07-12T02:37:22.937Z", "recordings": [ { "recording_id": "2fa19447117b87d7c4eaebbd209383a38e32aad5270ec1d06a4b6f5c7d3993c7", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6a8/6a8a03514b1d9d5b0edc876cc61632fea258b6a73e2f5c93e19476961b0e717a.mp3", "archive_relative_path": "raw/audio/6a8/6a8a03514b1d9d5b0edc876cc61632fea258b6a73e2f5c93e19476961b0e717a.mp3" } ] } ], "prediction": "Pugwelji'jig ta'n tujiw maljewe'ji'jit.", "reference": "Qospemji'jg etlia'sugwesugwijig." }, { "id": "mic-sent-32b5be58f0ffd82d62ce67e4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who did something to my dog?", "output_text": "Wen gisna'tala'latl nti'l?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who did something to my dog?", "mic_Latn": "Wen gisna'tala'latl nti'l?" }, "canonical_ref": "entries/n/na'tala'latl/na'tala'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-390e8af62aabcddadf0b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/na'tala'latl/na'tala'latl.html", "entry_url": "https://mikmaqonline.org/entries/n/na'tala'latl/na'tala'latl.html", "headword": "na'tala'latl", "example_index": 0, "raw_html_path": "raw/entries/81fb4214486b4a03cec8db79ce55e0080e63ccf6518ae27d7fd6facd0d266296.html", "raw_html_sha256": "a78b2441ec307ef38a72a520cc854543100bf368963938332c0447b951813905", "fetched_at": "2026-07-12T02:42:09.874Z", "recordings": [ { "recording_id": "336c87ada3d29b47641b7f3ee918d8f6175a7521d6f31e7c9b080a862ce04605", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e2b/e2b12148b23ec3f3bd1bf5c2e9f4b5eaa22f61f32bfd0cd50705fbc2aa726016.mp3", "archive_relative_path": "raw/audio/e2b/e2b12148b23ec3f3bd1bf5c2e9f4b5eaa22f61f32bfd0cd50705fbc2aa726016.mp3" } ] } ], "prediction": "Wen gisga'toq ugti'l?", "reference": "Wen gisna'tala'latl nti'l?" }, { "id": "mic-sent-32d762f0a42e95665210e809:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Percy spends his days gathering bottles.", "output_text": "Pugus na tellugwet te'sigisg'g mawo'laji pu'taig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Percy spends his days gathering bottles.", "mic_Latn": "Pugus na tellugwet te'sigisg'g mawo'laji pu'taig." }, "canonical_ref": "entries/m/mawo'laji/mawo'laji.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3781aa9d979a47a9823c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mawo'laji/mawo'laji.html", "entry_url": "https://mikmaqonline.org/entries/m/mawo'laji/mawo'laji.html", "headword": "mawo'laji", "example_index": 0, "raw_html_path": "raw/entries/e2fa2847cbd2bd02153bd634ce3ebdb6935756be5fb7cca6ebf1e9311c42387f.html", "raw_html_sha256": "9f747f30607cf7c85558c2f6b76f958813e2962d7eb77bca30fd3a7aebdadd0c", "fetched_at": "2026-07-12T02:41:02.624Z", "recordings": [ { "recording_id": "07eb92b92ddc71d5b90e8bc31d9464c212f9577cfb5136402603f96a4014d22f", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/56e/56ede1f313ef180b3b559d2b76811b36679f0e3411311a19c653832872482192.mp3", "archive_relative_path": "raw/audio/56e/56ede1f313ef180b3b559d2b76811b36679f0e3411311a19c653832872482192.mp3" } ] } ], "prediction": "Pas'g gesgm'g ugjit pugs'g.", "reference": "Pugus na tellugwet te'sigisg'g mawo'laji pu'taig." }, { "id": "mic-sent-32feae4f6ed9575ab74f9a23:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she/it makes the ground hard by trampling it under foot before he/she begins to build his/her house.", "output_text": "Esnaqamiga'toq maqamigew gesgmnaq ewi'gagw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she/it makes the ground hard by trampling it under foot before he/she begins to build his/her house.", "mic_Latn": "Esnaqamiga'toq maqamigew gesgmnaq ewi'gagw." }, "canonical_ref": "entries/e/esnaqamiga'toq/esnaqamiga'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5bec70292e29ebd69851", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/esnaqamiga'toq/esnaqamiga'toq.html", "entry_url": "https://mikmaqonline.org/entries/e/esnaqamiga'toq/esnaqamiga'toq.html", "headword": "esnaqamiga'toq", "example_index": 0, "raw_html_path": "raw/entries/8fdd02880c439c2e7c8f63622c364c5c00879f1012439b63266bb3369c58ee26.html", "raw_html_sha256": "7a7e4d9d564693de5d9e82a7b73ba7fe8c95265f9c3396b2c79e2a6f2639626d", "fetched_at": "2026-07-12T02:38:17.267Z", "recordings": [ { "recording_id": "0d10c9b5b7dc20461ead96d558609525f7b88fa7c254db402456f4d3b93ac72c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/80d/80d389307206e1f34b8be44aac7ddf1dd1d7d747c38cebaa9f200862a4aff852.mp3", "archive_relative_path": "raw/audio/80d/80d389307206e1f34b8be44aac7ddf1dd1d7d747c38cebaa9f200862a4aff852.mp3" } ] } ], "prediction": "Pugwelga'latl ta'n tujiw gesgmnaq gmu'j ugjit.", "reference": "Esnaqamiga'toq maqamigew gesgmnaq ewi'gagw." }, { "id": "mic-sent-3337079688a93954eef57fde:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My grand child has a cold today.", "output_text": "Nuji'j tgeia'tat gisgug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My grand child has a cold today.", "mic_Latn": "Nuji'j tgeia'tat gisgug." }, "canonical_ref": "entries/t/tgeia'tat/tgeia'tat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-72c07c42beaa48dba744", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tgeia'tat/tgeia'tat.html", "entry_url": "https://mikmaqonline.org/entries/t/tgeia'tat/tgeia'tat.html", "headword": "tgeia'tat", "example_index": 0, "raw_html_path": "raw/entries/b7da949df8dff1130262c211b8db835b1d1f0040ed6f6b4fafce68a8b05e0fc4.html", "raw_html_sha256": "8be1f834b29bbd1425dcd3a51e5928d0f2349ebedf898c0331b9639a64c32cf3", "fetched_at": "2026-07-12T02:45:56.019Z", "recordings": [ { "recording_id": "1b5de175b24f07b5de8eb7244beca3ffa7d0e4035b408190b24b620f37772054", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/52f/52fcbe6437e7deb73366d247ad9308857dadac424f8f1150a0f47757106c81fb.mp3", "archive_relative_path": "raw/audio/52f/52fcbe6437e7deb73366d247ad9308857dadac424f8f1150a0f47757106c81fb.mp3" } ] } ], "prediction": "Nuji'j gis gisgug.", "reference": "Nuji'j tgeia'tat gisgug." }, { "id": "mic-sent-333fcacd7f16126c746dc3a1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There are lots of fruit bushes here.", "output_text": "Mawpugwelgig tet na amalo'qomanimusi'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There are lots of fruit bushes here.", "mic_Latn": "Mawpugwelgig tet na amalo'qomanimusi'g." }, "canonical_ref": "entries/a/amalo'qomanimusi/amalo'qomanimusi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b450af0e9d45375c24c1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amalo'qomanimusi/amalo'qomanimusi.html", "entry_url": "https://mikmaqonline.org/entries/a/amalo'qomanimusi/amalo'qomanimusi.html", "headword": "amalo'qomanimusi", "example_index": 0, "raw_html_path": "raw/entries/0253d4eee5427bf1455a38bf9b7edac25e6efcca048c61a608ff5b1ed7770e9d.html", "raw_html_sha256": "2dac745bc060d5a0afba639658237c2b1aa128860df08dec7109cfa5f136a88c", "fetched_at": "2026-07-12T02:36:26.055Z", "recordings": [ { "recording_id": "3eaba6199b5c4a14f62ddbd5264327d8ae8d3aeb5fa30f837bbf42cad67efc0d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8a4/8a4402cf3d4506055a3e069a25e7f7e0d66f261f54fecc71b08c020d1cd6ffe4.mp3", "archive_relative_path": "raw/audio/8a4/8a4402cf3d4506055a3e069a25e7f7e0d66f261f54fecc71b08c020d1cd6ffe4.mp3" } ] } ], "prediction": "Pugwelg'g ugjit gmu'jig ula tet.", "reference": "Mawpugwelgig tet na amalo'qomanimusi'g." }, { "id": "mic-sent-338ef52d3fdf552187a0ce4c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My dog is acting differently, perhaps tomorrow is going to be a stormy day.", "output_text": "Mtugunoqtnugwet ntue'm, etug getu mamunigisgug sapo'nug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My dog is acting differently, perhaps tomorrow is going to be a stormy day.", "mic_Latn": "Mtugunoqtnugwet ntue'm, etug getu mamunigisgug sapo'nug." }, "canonical_ref": "entries/m/mtugunoqtnugwet/mtugunoqtnugwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6249f28623faa78935f0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mtugunoqtnugwet/mtugunoqtnugwet.html", "entry_url": "https://mikmaqonline.org/entries/m/mtugunoqtnugwet/mtugunoqtnugwet.html", "headword": "mtugunoqtnugwet", "example_index": 0, "raw_html_path": "raw/entries/a94bf0a44a2282f19b48f94a0e9495c7592d1328ab389ca51f0a4e99aecaecd3.html", "raw_html_sha256": "4d42a9e5fca9b4967c9844f0cd6a99aefe4fd006c0d9a923a62fb833ac5a8b11", "fetched_at": "2026-07-12T02:41:47.448Z", "recordings": [ { "recording_id": "0faa1dfbb5e5c9f61c8124a7c53840a9df54ddc00ec774778b373bdf701b01c7", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/617/617ea810a57435e047abcaa955fdb39844790c545f3598e277c55fec2ec6d5e9.mp3", "archive_relative_path": "raw/audio/617/617ea810a57435e047abcaa955fdb39844790c545f3598e277c55fec2ec6d5e9.mp3" } ] } ], "prediction": "Nmu'ji'j na nmu'j, gatu gisgug we'gwigsitpu'g.", "reference": "Mtugunoqtnugwet ntue'm, etug getu mamunigisgug sapo'nug." }, { "id": "mic-sent-33eb657a50292fc2df7cdb44:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend is a French woman.", "output_text": "Nitape'sgw na wenjujgwej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend is a French woman.", "mic_Latn": "Nitape'sgw na wenjujgwej." }, "canonical_ref": "entries/w/wenjujgwej/wenjujgwej.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9cf86e4ce07b91d73603", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wenjujgwej/wenjujgwej.html", "entry_url": "https://mikmaqonline.org/entries/w/wenjujgwej/wenjujgwej.html", "headword": "wenjujgwej", "example_index": 0, "raw_html_path": "raw/entries/92b613e119310a84531c5cd2c545fbaecd49f3a6ab024c55a8034460ab6989d1.html", "raw_html_sha256": "c6c9811ef95227a92f3330122c0ac14b4022f1fd46cda2c959ba4a955bdc84be", "fetched_at": "2026-07-12T02:47:13.226Z", "recordings": [ { "recording_id": "87d7a5d1eb17555769777bea0fcee06ca10fccdd31e9393f287f09f83ae8c697", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/238/2388cef36d3b43eb510910221895e2a74ad52b28ec4da67ee322d4b7946cf7a3.mp3", "archive_relative_path": "raw/audio/238/2388cef36d3b43eb510910221895e2a74ad52b28ec4da67ee322d4b7946cf7a3.mp3" } ] } ], "prediction": "Nitap na we'gwi'g.", "reference": "Nitape'sgw na wenjujgwej." }, { "id": "mic-sent-33f7eb965798b3174486da08:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend is the best hunter.", "output_text": "Nitap na mawglu'sit nutanteget.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend is the best hunter.", "mic_Latn": "Nitap na mawglu'sit nutanteget." }, "canonical_ref": "entries/n/nutanteget/nutanteget.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-751e9c002d51b5fa5ee5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nutanteget/nutanteget.html", "entry_url": "https://mikmaqonline.org/entries/n/nutanteget/nutanteget.html", "headword": "nutanteget", "example_index": 1, "raw_html_path": "raw/entries/c9b34750a28a3a87b533fb1c309bca8b838540e3559d064ed50e5e8c47f8a836.html", "raw_html_sha256": "a6818f45f81106486cc8af2817b20be539430fde86043e2e2b3a0b92598f23b4", "fetched_at": "2026-07-12T02:42:55.023Z", "recordings": [ { "recording_id": "7420aa9c1fd4bb8cef7a5d0954322901d65dd83043a23303a3210da9491966a5", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4f1/4f15d2d97f2c8dc259c7b7c282ced9cc471c71869d2513618ce58781d62e5db1.mp3", "archive_relative_path": "raw/audio/4f1/4f15d2d97f2c8dc259c7b7c282ced9cc471c71869d2513618ce58781d62e5db1.mp3" } ] } ], "prediction": "Nitap na we'gwi'ji'j.", "reference": "Nitap na mawglu'sit nutanteget." }, { "id": "mic-sent-34348010683d4a3a04c0b7dc:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Would you bring me one wrapper.", "output_text": "Ge juga'wtui newte' loqomoqwa'taqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Would you bring me one wrapper.", "mic_Latn": "Ge juga'wtui newte' loqomoqwa'taqan." }, "canonical_ref": "entries/l/loqomoqwa'taqan/loqomoqwa'taqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a2c62d688acf1b72dbcd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/loqomoqwa'taqan/loqomoqwa'taqan.html", "entry_url": "https://mikmaqonline.org/entries/l/loqomoqwa'taqan/loqomoqwa'taqan.html", "headword": "loqomoqwa'taqan", "example_index": 0, "raw_html_path": "raw/entries/0cb954301d6fc321d48e1b1f558742c3bdfbf5a6a74583939f6d5817dc8cfbdd.html", "raw_html_sha256": "44519959f5224a2839e632c034ff83d248d8f3b7d4f0696e67424ce3c031fd7d", "fetched_at": "2026-07-12T02:40:38.010Z", "recordings": [ { "recording_id": "30af6bec6ee4e04f67df6ffcaa3a0f7b8aaaf079a0c9f35e871925e89b1e99d8", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e52/e52e2606b780522e15d2beae7e0911dd5c772366226e1dd98883cd5112b15587.mp3", "archive_relative_path": "raw/audio/e52/e52e2606b780522e15d2beae7e0911dd5c772366226e1dd98883cd5112b15587.mp3" } ] } ], "prediction": "Ge' jugwa'latl newte'g.", "reference": "Ge juga'wtui newte' loqomoqwa'taqan." }, { "id": "mic-sent-343f744d396013822f8f4bd8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The way my dog is drinking, he/she must have been thirsty.", "output_text": "Ta'n telinsapoqwaj nti, miamuj niwipsguna'tug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The way my dog is drinking, he/she must have been thirsty.", "mic_Latn": "Ta'n telinsapoqwaj nti, miamuj niwipsguna'tug." }, "canonical_ref": "entries/n/nessapoqwat/nessapoqwat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6f11de7755b3ca5cfb5a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nessapoqwat/nessapoqwat.html", "entry_url": "https://mikmaqonline.org/entries/n/nessapoqwat/nessapoqwat.html", "headword": "nessapoqwat", "example_index": 0, "raw_html_path": "raw/entries/a0b93bbb120d5ca64b48b1beb8ced22719e601347090e562d1cba63e68688ffe.html", "raw_html_sha256": "4307be5e774fff8ed58027d5e8a1e4ac7d392d78b723f97d0980c39caf01cbf8", "fetched_at": "2026-07-12T02:42:23.148Z", "recordings": [ { "recording_id": "6453834f314fb60bf60a723b0bac31d53770c5f4371cc2e2e65beba7d19dad29", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/87d/87d29278e7fa33d010e889d22773c50efca747380dddbb8f31d18b556fa8e4a2.mp3", "archive_relative_path": "raw/audio/87d/87d29278e7fa33d010e889d22773c50efca747380dddbb8f31d18b556fa8e4a2.mp3" } ] } ], "prediction": "Nmu'j nmu'ji'j gesgmnaq, amujpa gisgugwet.", "reference": "Ta'n telinsapoqwaj nti, miamuj niwipsguna'tug." }, { "id": "mic-sent-3484591bc40f82aedec737fe:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little dog chokes while over-eating.", "output_text": "Lpa nmu'ji'j noqt'g ge's gi'gatatalg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little dog chokes while over-eating.", "mic_Latn": "Lpa nmu'ji'j noqt'g ge's gi'gatatalg." }, "canonical_ref": "entries/n/noqt'g/noqt'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1ed964f2729d018a0a89", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/noqt'g/noqt'g.html", "entry_url": "https://mikmaqonline.org/entries/n/noqt'g/noqt'g.html", "headword": "noqt'g", "example_index": 0, "raw_html_path": "raw/entries/a8841b0a35ff5d111fe3454f9f8febed0ff4550a7d9c9c1844ad866ce434eba8.html", "raw_html_sha256": "57c5592b15abd43c46f89971fbd09d1ce2264d80a49f8afbe0b83f25388a7878", "fetched_at": "2026-07-12T02:42:42.263Z", "recordings": [ { "recording_id": "95a411e55dd078434c4d2666efb26db8d6f4761d005f950efce9b79b50ce0f03", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b71/b71356c29db7f06c8083af84aca0b366af22cfaa13e15627cc07f9f9c62470ee.mp3", "archive_relative_path": "raw/audio/b71/b71356c29db7f06c8083af84aca0b366af22cfaa13e15627cc07f9f9c62470ee.mp3" } ] } ], "prediction": "E'pite'ji'j gesatg ta'n te'sipow.", "reference": "Lpa nmu'ji'j noqt'g ge's gi'gatatalg." }, { "id": "mic-sent-34b71c154355ca7be1ba64de:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When he/she remembered what he/she meant to ask him/her, he/she ran after him/her.", "output_text": "Migwite'tgeg tawoqwei getu pipanimapnn, poqt'tesguapnn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When he/she remembered what he/she meant to ask him/her, he/she ran after him/her.", "mic_Latn": "Migwite'tgeg tawoqwei getu pipanimapnn, poqt'tesguapnn." }, "canonical_ref": "entries/p/poqt'tesguatl/poqt'tesguatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-844adcba4e71742283f8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/poqt'tesguatl/poqt'tesguatl.html", "entry_url": "https://mikmaqonline.org/entries/p/poqt'tesguatl/poqt'tesguatl.html", "headword": "poqt'tesguatl", "example_index": 0, "raw_html_path": "raw/entries/3cb72c8c657dfc684402c6c2e46a45979052097e386bc4c9f22d8da97fd4f343.html", "raw_html_sha256": "4c031707ec45bf2fbc58f6b96a2ac6743e033e93ea2a6a50fd7e521d91ba0e8a", "fetched_at": "2026-07-12T02:44:17.134Z", "recordings": [ { "recording_id": "ca203a32e3803e07c0c7cf18d232a0832a3b42be77192996f1d0fe0d3952030c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b97/b9798fc59a0beb8473a97d45b3c3c75ddbfe9f97efb9f2f5e65712a8bd8414e3.mp3", "archive_relative_path": "raw/audio/b97/b9798fc59a0beb8473a97d45b3c3c75ddbfe9f97efb9f2f5e65712a8bd8414e3.mp3" } ] } ], "prediction": "Ta'n te's'g ta'n tujiw telte'l, pemiet.", "reference": "Migwite'tgeg tawoqwei getu pipanimapnn, poqt'tesguapnn." }, { "id": "mic-sent-34c48c76dc97b501e0e7e32d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The Saint Anne's Day is a big feast day.", "output_text": "Se'tane'umg na mesgi'g na'gweg pestie'wumg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The Saint Anne's Day is a big feast day.", "mic_Latn": "Se'tane'umg na mesgi'g na'gweg pestie'wumg." }, "canonical_ref": "entries/p/pestie'wumg/pestie'wumg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3288699f1361b8b9c3c6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pestie'wumg/pestie'wumg.html", "entry_url": "https://mikmaqonline.org/entries/p/pestie'wumg/pestie'wumg.html", "headword": "pestie'wumg", "example_index": 0, "raw_html_path": "raw/entries/a5b884f94fc5aadf150eebb5632de25e33276daa9945dd329eb16326c3bdc2b4.html", "raw_html_sha256": "b9bfb767b51bf387a3ada79c54604fff13dc943a09ab8afdb7325ae46e8f71d6", "fetched_at": "2026-07-12T02:43:46.894Z", "recordings": [ { "recording_id": "634371652a4766df883e1f4de77c2ea5f748d1a17d86f42feec6e312a810eb8e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c06/c0674203a155701d7f46351fa8220779a14d0fcfb5c43b0de998b05f64847829.mp3", "archive_relative_path": "raw/audio/c06/c0674203a155701d7f46351fa8220779a14d0fcfb5c43b0de998b05f64847829.mp3" } ] } ], "prediction": "Sa'ne's'g na mawigsitg.", "reference": "Se'tane'umg na mesgi'g na'gweg pestie'wumg." }, { "id": "mic-sent-3505d0758213177287f97343:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He gossips at the Restigouche Drive-Thru.", "output_text": "Pusgialagnutg Restigouche Drive-Thru.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He gossips at the Restigouche Drive-Thru.", "mic_Latn": "Pusgialagnutg Restigouche Drive-Thru." }, "canonical_ref": "entries/p/pusgialagnutg/pusgialagnutg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a3f017fc3e5201b5568b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pusgialagnutg/pusgialagnutg.html", "entry_url": "https://mikmaqonline.org/entries/p/pusgialagnutg/pusgialagnutg.html", "headword": "pusgialagnutg", "example_index": 0, "raw_html_path": "raw/entries/7f14c997602bd3de25a078879fee0ceeaa36ee2a4916fd03e0b0a4d5a7526cd4.html", "raw_html_sha256": "147c212b953b937cc9019934aa985307f482feac188ae7a179deb04e148a4893", "fetched_at": "2026-07-12T02:44:28.086Z", "recordings": [ { "recording_id": "7398f9d074f7531025a6aba724fa0fc0d4e3e73bfbb07e38752d0ef07e2920fc", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/db4/db446e526937bc78c3e04e9597e6a9a1c4e8accc804a857bef430c40158b876f.mp3", "archive_relative_path": "raw/audio/db4/db446e526937bc78c3e04e9597e6a9a1c4e8accc804a857bef430c40158b876f.mp3" } ] } ], "prediction": "Pugwelga'latl Restigouge'g Drive-Thru.", "reference": "Pusgialagnutg Restigouche Drive-Thru." }, { "id": "mic-sent-35539fb2e33d7321eb518890:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's now exactly three o'clock.", "output_text": "Assma nige' si'st ajiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's now exactly three o'clock.", "mic_Latn": "Assma nige' si'st ajiet." }, "canonical_ref": "entries/a/assma/assma.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0f94fb702b690d4d4385", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/assma/assma.html", "entry_url": "https://mikmaqonline.org/entries/a/assma/assma.html", "headword": "assma", "example_index": 0, "raw_html_path": "raw/entries/8c812641bc06aa7739d499cb757fbc069a715e7604f9a559d5148be4650ee75c.html", "raw_html_sha256": "b3d01f1944857f625dc6cbd5e8b473b203271dadfce3d82f1fc72d94fac72c8f", "fetched_at": "2026-07-12T02:37:22.429Z", "recordings": [ { "recording_id": "9800707d3f4ba49df43fd2a998103f763e1f567ffce01c01f00e25fe3e628897", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d12/d12a734cd72c0f2f824c636c073955d5d1495c4685f71d61945b64dc1a8f7a5c.mp3", "archive_relative_path": "raw/audio/d12/d12a734cd72c0f2f824c636c073955d5d1495c4685f71d61945b64dc1a8f7a5c.mp3" } ] } ], "prediction": "Gi's nige' pas'g newte'g.", "reference": "Assma nige' si'st ajiet." }, { "id": "mic-sent-3569d6041bffe5f62af4d5a0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Is that door open?", "output_text": "Panteteg na ga'qan?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Is that door open?", "mic_Latn": "Panteteg na ga'qan?" }, "canonical_ref": "entries/p/panteteg/panteteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6d3e78e2cef61d556384", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/panteteg/panteteg.html", "entry_url": "https://mikmaqonline.org/entries/p/panteteg/panteteg.html", "headword": "panteteg", "example_index": 0, "raw_html_path": "raw/entries/457ff09ea253077e55ac9a03242bdee069dde1faaa879996ca91d5b946d9b936.html", "raw_html_sha256": "6b56721f19816f5a263aba6c822f710cce24e90a96572369482cdb4954891fca", "fetched_at": "2026-07-12T02:43:07.177Z", "recordings": [ { "recording_id": "b52ee57b1fb1e66f5a85dc5b6a1ebec84fcbfdd76bf6c4f80ff0f2a3a11792f2", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dc3/dc3770ce6c8b200d39b9246d367cddfe24fc3bfc0f86f6beed200e9d9da94d2c.mp3", "archive_relative_path": "raw/audio/dc3/dc3770ce6c8b200d39b9246d367cddfe24fc3bfc0f86f6beed200e9d9da94d2c.mp3" } ] } ], "prediction": "Gesat na ga'qan?", "reference": "Panteteg na ga'qan?" }, { "id": "mic-sent-35b2566aa76bf7591501e431:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This wood they brought is just for the fire.", "output_text": "Ula pugsug pegisitu'tij pas'g pugtewei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This wood they brought is just for the fire.", "mic_Latn": "Ula pugsug pegisitu'tij pas'g pugtewei." }, "canonical_ref": "entries/p/pugtewei/pugtewei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f87941d0f47b4f2b03cd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pugtewei/pugtewei.html", "entry_url": "https://mikmaqonline.org/entries/p/pugtewei/pugtewei.html", "headword": "pugtewei", "example_index": 0, "raw_html_path": "raw/entries/c017c24aeee79ab2bc5955ac6b2d085fca24a81f297f71e633f2814647a4408a.html", "raw_html_sha256": "04ef0db3dc6978bcc409db8b5eb65318e11d6249b9bc128db22e1c7a62c50135", "fetched_at": "2026-07-12T02:36:07.734Z", "recordings": [ { "recording_id": "c297337a5e15f8756b064e2420eac12ecca459e1f08d9efad10172d4a48527f4", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7da/7da6f81aa582e08d1e8f499d4357f24cf0b1b7746ab27650fba0ccc6adb8539d.mp3", "archive_relative_path": "raw/audio/7da/7da6f81aa582e08d1e8f499d4357f24cf0b1b7746ab27650fba0ccc6adb8539d.mp3" } ] } ], "prediction": "Pugwelg na ula gmu'ji'j na pas'g wesgowaqan.", "reference": "Ula pugsug pegisitu'tij pas'g pugtewei." }, { "id": "mic-sent-368f57dbb8bca8fa4867cc62:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Because he/she persisted in working at it, at last it is done.", "output_text": "Ge's gi'gaj elugwatg, glapis gisa'to'q.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Because he/she persisted in working at it, at last it is done.", "mic_Latn": "Ge's gi'gaj elugwatg, glapis gisa'to'q." }, "canonical_ref": "entries/g/gi'gaj/gi'gaj.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bed349993fd3513268ca", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gi'gaj/gi'gaj.html", "entry_url": "https://mikmaqonline.org/entries/g/gi'gaj/gi'gaj.html", "headword": "gi'gaj", "example_index": 0, "raw_html_path": "raw/entries/d3e82fa6a9185353d8668d79c80aa9049c109b64a30acd7bae7c2d4ebb85195c.html", "raw_html_sha256": "1e33d395b4604d6f8e5b59f877dd4909fa6528243f7858245b36ac39235af979", "fetched_at": "2026-07-12T02:39:28.206Z", "recordings": [ { "recording_id": "fbded3f5912389491374a55c47c371df938a0d177755f0831d465244adc2c68f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c9c/c9cb8d57f20d805cae3017368557b323040f283d41559ac5d9585826c06adb33.mp3", "archive_relative_path": "raw/audio/c9c/c9cb8d57f20d805cae3017368557b323040f283d41559ac5d9585826c06adb33.mp3" } ] } ], "prediction": "Ta'n gisg'pugwelg ta'n tujiw, gi's gisipugwet.", "reference": "Ge's gi'gaj elugwatg, glapis gisa'to'q." }, { "id": "mic-sent-36cc80edd502db3fc5062ebf:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The young child walks in and asks for food.", "output_text": "Mijua'ji'j pisgwa't aq pipanigesij nana'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The young child walks in and asks for food.", "mic_Latn": "Mijua'ji'j pisgwa't aq pipanigesij nana'n." }, "canonical_ref": "entries/n/nana'n/nana'n.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-06679b43b16197f70993", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nana'n/nana'n.html", "entry_url": "https://mikmaqonline.org/entries/n/nana'n/nana'n.html", "headword": "nana'n", "example_index": 0, "raw_html_path": "raw/entries/2f93938f1fc9a5cd0d806abd61e618fc0783ce976042a8d3cf9ef7daee123239.html", "raw_html_sha256": "ffc440e122c4a7bb88637b176d21e63145d171056be6476e178925b76af24306", "fetched_at": "2026-07-12T02:41:58.070Z", "recordings": [ { "recording_id": "ed4147685426803b189892c22a53f8455eb3ea5973fdabcd31e48bf309d84a00", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7b7/7b75702cc635df6a21ad0d455439c68cf1297f87f66090a2dea948d70efc50ff.mp3", "archive_relative_path": "raw/audio/7b7/7b75702cc635df6a21ad0d455439c68cf1297f87f66090a2dea948d70efc50ff.mp3" } ] } ], "prediction": "Lpa'tuji'j etli'g aq pemiet.", "reference": "Mijua'ji'j pisgwa't aq pipanigesij nana'n." }, { "id": "mic-sent-3727e5071123f971ad4bd871:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she quarantines him/her at his/her home.", "output_text": "Amnapegalatl wiguaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she quarantines him/her at his/her home.", "mic_Latn": "Amnapegalatl wiguaq." }, "canonical_ref": "entries/a/amnapegalatl/amnapegalatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4ef902c40052693c5a57", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amnapegalatl/amnapegalatl.html", "entry_url": "https://mikmaqonline.org/entries/a/amnapegalatl/amnapegalatl.html", "headword": "amnapegalatl", "example_index": 0, "raw_html_path": "raw/entries/2fc762e7a13e15314498dfb9632ad3914472595e9da4198496da248095892bc9.html", "raw_html_sha256": "628bbead80a8af083b18e19a4135dfb8bfadc839458ddf49611d7688bd9968b8", "fetched_at": "2026-07-12T02:36:54.256Z", "recordings": [ { "recording_id": "c54abf5dbbb092874959c2673469c29178db644a32d9d3491bd85db4b7c05a1d", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/569/5698254cd6ce41236190358bc084ec85e4c4e4c481d2f127f5a6fc3e19f172ff.mp3", "archive_relative_path": "raw/audio/569/5698254cd6ce41236190358bc084ec85e4c4e4c481d2f127f5a6fc3e19f172ff.mp3" } ] } ], "prediction": "Lpa ugta'latl ugjit.", "reference": "Amnapegalatl wiguaq." }, { "id": "mic-sent-37452f5965de6efbec4d369b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The boards are leaning up against the fence.", "output_text": "Llutaqanigtug epatgwepultijig lasqo'plaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The boards are leaning up against the fence.", "mic_Latn": "Llutaqanigtug epatgwepultijig lasqo'plaq." }, "canonical_ref": "entries/e/epatgwepit/epatgwepit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3a8960dcf09cf42a727b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/epatgwepit/epatgwepit.html", "entry_url": "https://mikmaqonline.org/entries/e/epatgwepit/epatgwepit.html", "headword": "epatgwepit", "example_index": 0, "raw_html_path": "raw/entries/a2dd95e66c6f7fe13a0ff40df1382635fd7e272a200bd029f81dfba86520e5fe.html", "raw_html_sha256": "134ae49b44f808e1a6886c8eaf50d2ce5e8f49079a3a4e40f1778abf05a5696a", "fetched_at": "2026-07-12T02:38:07.217Z", "recordings": [ { "recording_id": "99a5a54b90b06c843e52c55d32c5d0779b496ca7a4f109b9ffebedc18a437423", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5bd/5bd3b1c62259ff79834c6bee08585b4d41225c04e9970f3173fb2f0c8bbf676d.mp3", "archive_relative_path": "raw/audio/5bd/5bd3b1c62259ff79834c6bee08585b4d41225c04e9970f3173fb2f0c8bbf676d.mp3" } ] } ], "prediction": "Pugwelg'p't'g na lpa wi'gwigtug.", "reference": "Llutaqanigtug epatgwepultijig lasqo'plaq." }, { "id": "mic-sent-3751f682e2305aa5453cacf0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Don't reuse that rinse water.", "output_text": "Mutt ilie'wmu na siguapatign.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Don't reuse that rinse water.", "mic_Latn": "Mutt ilie'wmu na siguapatign." }, "canonical_ref": "entries/s/siguapatign/siguapatign.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d8f3d7ebeadb3cc0abc2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/siguapatign/siguapatign.html", "entry_url": "https://mikmaqonline.org/entries/s/siguapatign/siguapatign.html", "headword": "siguapatign", "example_index": 0, "raw_html_path": "raw/entries/d9887937dc3a793b3e16add00b93baecf78b2ef62222723c45dbf92fab680691.html", "raw_html_sha256": "c3575fa6337853c2f5d93b4a98eb20c155f864c1c44e07eafc5d0843cb04a7d5", "fetched_at": "2026-07-12T02:45:01.853Z", "recordings": [ { "recording_id": "8e7611a8a5f14e0b21bab79a93488c835f9338c67595d332a379c66f9b483a83", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d41/d410a884c93b7a718b0e70f0286aeeb175923591eae21591e0d5628f2d7d5bb9.mp3", "archive_relative_path": "raw/audio/d41/d410a884c93b7a718b0e70f0286aeeb175923591eae21591e0d5628f2d7d5bb9.mp3" } ] } ], "prediction": "Mu' newte'g na lugowaqan.", "reference": "Mutt ilie'wmu na siguapatign." }, { "id": "mic-sent-37a7d62c61e97260ed3e5f13:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "S/he has plenty of that kind of rope.", "output_text": "Pugwennatl na telamugsinitl a'papi'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "S/he has plenty of that kind of rope.", "mic_Latn": "Pugwennatl na telamugsinitl a'papi'l." }, "canonical_ref": "entries/p/pugwennatl/pugwennatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4f3eb806407edfe017b3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pugwennatl/pugwennatl.html", "entry_url": "https://mikmaqonline.org/entries/p/pugwennatl/pugwennatl.html", "headword": "pugwennatl", "example_index": 0, "raw_html_path": "raw/entries/5960d299aef04a3de0e17d33046ab6f838210795e51ff3354af3826a9a9d3c19.html", "raw_html_sha256": "e0870c09d67f12fb83bedd446c4dab38c67ea9a5816556b81ae8a77266990e6e", "fetched_at": "2026-07-12T02:44:25.073Z", "recordings": [ { "recording_id": "2ce565b8aa4bf9a2df6c2992d1ce487315648205b6919eecbd8f9a28d5539bb7", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9d0/9d0d09f154243a310057d70da3111fea4076c8be3cd94969cf91f92dbd0ec124.mp3", "archive_relative_path": "raw/audio/9d0/9d0d09f154243a310057d70da3111fea4076c8be3cd94969cf91f92dbd0ec124.mp3" } ] } ], "prediction": "Pugwelg na gmu'j.", "reference": "Pugwennatl na telamugsinitl a'papi'l." }, { "id": "mic-sent-37cfab94993d95c2ffae2f87:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she uses an ax when felling a tree.", "output_text": "Negm tmi'gnta'tl miti'sl ta'n tujiw gewa'laj.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she uses an ax when felling a tree.", "mic_Latn": "Negm tmi'gnta'tl miti'sl ta'n tujiw gewa'laj." }, "canonical_ref": "entries/t/tmi'gnta'tl/tmi'gnta'tl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-904953d8d7a00bada4e0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tmi'gnta'tl/tmi'gnta'tl.html", "entry_url": "https://mikmaqonline.org/entries/t/tmi'gnta'tl/tmi'gnta'tl.html", "headword": "tmi'gnta'tl", "example_index": 0, "raw_html_path": "raw/entries/6510c73d1d22dabd4dcba9d87bd09eb3584f4c7701ee2861b90cfa4d5f6d04db.html", "raw_html_sha256": "c5592905e546195173eaea95599606c1fb58b32610c01ea197c3d0e4b3d3bdac", "fetched_at": "2026-07-12T02:46:00.637Z", "recordings": [ { "recording_id": "edb84d3193a46835f08fb470b28a5d0d7d31696a956fc1bcf1dd8a81ece9ee70", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/004/0044c8adaf6529985ae1d93dcbd73fc7c06fed8a9da2867d1a84315ec52dabe9.mp3", "archive_relative_path": "raw/audio/004/0044c8adaf6529985ae1d93dcbd73fc7c06fed8a9da2867d1a84315ec52dabe9.mp3" } ] } ], "prediction": "Ugo'toq na gmu'j ta'n tujiw miti'j.", "reference": "Negm tmi'gnta'tl miti'sl ta'n tujiw gewa'laj." }, { "id": "mic-sent-38320cb1da8b5ca53b55d377:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That net you are using is in bad condition.", "output_text": "Winjit na a'pi etlie'w't.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That net you are using is in bad condition.", "mic_Latn": "Winjit na a'pi etlie'w't." }, "canonical_ref": "entries/w/winjit/winjit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f07ed7d87d667d7e566b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/winjit/winjit.html", "entry_url": "https://mikmaqonline.org/entries/w/winjit/winjit.html", "headword": "winjit", "example_index": 0, "raw_html_path": "raw/entries/a1d36b70c7e870bc9ae52814febfb58ad97775b6412d4e438ce0392db537d019.html", "raw_html_sha256": "94651eb4b96e5aa17a2c8514959f4736ff7737c3988897c4b664695c492a78ff", "fetched_at": "2026-07-12T02:47:36.053Z", "recordings": [ { "recording_id": "7a74ffd2a6fad19c0aee7cc10ab79cc8c2a0143b389f3582f5de57d0f04976b0", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e86/e86c28cde01b459f372e932ca34fe198d55013e4d19cc0928961b48512ac4d03.mp3", "archive_relative_path": "raw/audio/e86/e86c28cde01b459f372e932ca34fe198d55013e4d19cc0928961b48512ac4d03.mp3" } ] } ], "prediction": "We'gwi'g na nuji'j na gmu'j.", "reference": "Winjit na a'pi etlie'w't." }, { "id": "mic-sent-38410ef3a463a6ceecfb617f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I try to take good care of my body.", "output_text": "Wejo'tm uliango'tmn ntinin.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I try to take good care of my body.", "mic_Latn": "Wejo'tm uliango'tmn ntinin." }, "canonical_ref": "entries/u/ugtinin/ugtinin.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7ed097fe5961b7fba7df", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugtinin/ugtinin.html", "entry_url": "https://mikmaqonline.org/entries/u/ugtinin/ugtinin.html", "headword": "ugtinin", "example_index": 0, "raw_html_path": "raw/entries/21eb91a3424288370fd74722aeb478e8866b2c9823138dd36fc550265457aefb.html", "raw_html_sha256": "cafaff3c487a635fb590c2499a7c7b0f24247f6baadea65929dc9026a0170779", "fetched_at": "2026-07-12T02:46:17.944Z", "recordings": [ { "recording_id": "3623253d21022b0bdffa19854b6f55f92140ab857d4f2b0d90cf2b24d2b33445", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/038/038750a332c429a55bb77c4e08e89c10dd021da702c58c60f82297c8d9471a9a.mp3", "archive_relative_path": "raw/audio/038/038750a332c429a55bb77c4e08e89c10dd021da702c58c60f82297c8d9471a9a.mp3" } ] } ], "prediction": "Ge' negm na nugu' ni'n goqwei.", "reference": "Wejo'tm uliango'tmn ntinin." }, { "id": "mic-sent-385ce3d19931e5af182c6206:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This old man is fun to be with.", "output_text": "Ula gisigu mawgise'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This old man is fun to be with.", "mic_Latn": "Ula gisigu mawgise'g." }, "canonical_ref": "entries/g/gise'g/gise'g.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c29011ca1627e8084639", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gise'g/gise'g.html", "entry_url": "https://mikmaqonline.org/entries/g/gise'g/gise'g.html", "headword": "gise'g", "example_index": 1, "raw_html_path": "raw/entries/087ba7f995048823d13a3bb2cbd7c10075770e985e163610f4781ba5d3448101.html", "raw_html_sha256": "7654d24fc0521c59d593360c1c8fcf3ddf7d9b58f35fb44a011247f6ba78b9f7", "fetched_at": "2026-07-12T02:39:36.653Z", "recordings": [ { "recording_id": "b19469b69ce7f76536b39d8b977675400fc6cd1b92a45345c41c522069fb0b4d", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5c0/5c0dc85b30b07fef0e21b6e0ad6432902242e775bd948c9078712bb8ea2ca779.mp3", "archive_relative_path": "raw/audio/5c0/5c0dc85b30b07fef0e21b6e0ad6432902242e775bd948c9078712bb8ea2ca779.mp3" } ] } ], "prediction": "Gisigu'g na ula gisigu.", "reference": "Ula gisigu mawgise'g." }, { "id": "mic-sent-388872fbd47db9a0e4bad6a7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has many gold chains.", "output_text": "Pugwengl wisawsulieweie'l pisga'taqanapi'ji'jl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has many gold chains.", "mic_Latn": "Pugwengl wisawsulieweie'l pisga'taqanapi'ji'jl." }, "canonical_ref": "entries/p/pisga'taqanapi'ji'j/pisga'taqanapi'ji'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-29e450699459aeaf1306", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pisga'taqanapi'ji'j/pisga'taqanapi'ji'j.html", "entry_url": "https://mikmaqonline.org/entries/p/pisga'taqanapi'ji'j/pisga'taqanapi'ji'j.html", "headword": "pisga'taqanapi'ji'j", "example_index": 0, "raw_html_path": "raw/entries/eb96910877707f85538e5dae3561b363c4cf496c37e893597f2fc9ac54ffaeca.html", "raw_html_sha256": "a5f712c4301854ae8ff3f92cac5f6abab4ae10149b58902e0483f6e18d8675b6", "fetched_at": "2026-07-12T02:44:02.171Z", "recordings": [ { "recording_id": "ad24be11d9d759dbbad09f8ba8ea331a201c031279ff94282c85a923c8f1f4c5", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c26/c260d8972eae2039d218122f3046d6145f6f122f7ef19b5f1e5f6b52a49cc6e7.mp3", "archive_relative_path": "raw/audio/c26/c260d8972eae2039d218122f3046d6145f6f122f7ef19b5f1e5f6b52a49cc6e7.mp3" } ] } ], "prediction": "Pugwelg'g na wi'gatign.", "reference": "Pugwengl wisawsulieweie'l pisga'taqanapi'ji'jl." }, { "id": "mic-sent-38b56044d9b12bcd8702f681:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My late uncle, Tom, always had a horse.", "output_text": "Ntlamugsisaq Tumao'q apjiw te'sipowl geggunapnn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My late uncle, Tom, always had a horse.", "mic_Latn": "Ntlamugsisaq Tumao'q apjiw te'sipowl geggunapnn." }, "canonical_ref": "entries/t/te'sipow/te'sipow.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-92be7439908cd5e70317", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/te'sipow/te'sipow.html", "entry_url": "https://mikmaqonline.org/entries/t/te'sipow/te'sipow.html", "headword": "te'sipow", "example_index": 0, "raw_html_path": "raw/entries/f2a3ea4aca69d8d74535ee2ed95b56e079a446809db6e9b4f67d1dded9e3ecc9.html", "raw_html_sha256": "15434f0cab2115e4ede8d8cc163ebc4cfe021a2d55bbac3742ccc1a6946f8c73", "fetched_at": "2026-07-12T02:45:45.450Z", "recordings": [ { "recording_id": "4bd6cda9507317dfc9e3e5e6bdd7faf3fc1cf37202ed807c457259f82a150f6d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9fd/9fdaa3c25d5cebe7bf7922873c8a5fb999407373ed29a7a98613782375cd020a.mp3", "archive_relative_path": "raw/audio/9fd/9fdaa3c25d5cebe7bf7922873c8a5fb999407373ed29a7a98613782375cd020a.mp3" } ] } ], "prediction": "Ntlugowa'ji'j, Tomu, te's te'sipowji'jit.", "reference": "Ntlamugsisaq Tumao'q apjiw te'sipowl geggunapnn." }, { "id": "mic-sent-39424bb7951774e5ac345b16:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I'll put the tea pot on to boil and we'll have tea.", "output_text": "Pe'l wesawa'l'g'p na p'teweio'q aq p'teweie'matesnu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I'll put the tea pot on to boil and we'll have tea.", "mic_Latn": "Pe'l wesawa'l'g'p na p'teweio'q aq p'teweie'matesnu." }, "canonical_ref": "entries/w/wesawa'latl/wesawa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3ff5caafdd8d22825e07", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wesawa'latl/wesawa'latl.html", "entry_url": "https://mikmaqonline.org/entries/w/wesawa'latl/wesawa'latl.html", "headword": "wesawa'latl", "example_index": 0, "raw_html_path": "raw/entries/a6477f66ada57718e8242529e6ddf3872122ddf5d4417661e30a1406d7b4f585.html", "raw_html_sha256": "8e1bd7587d98a8f579dd826758aaae315ceb3f945af6f954cb6146a697a1c52d", "fetched_at": "2026-07-12T02:47:15.935Z", "recordings": [ { "recording_id": "678535a4ef3bddaaaac0823ae348b3082e3cebeb1308927bb04fb05dc535632b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3ac/3ac061c22ded5792de0e056ffae7e4aba5e1037098cf8fee23e5733892fde3c1.mp3", "archive_relative_path": "raw/audio/3ac/3ac061c22ded5792de0e056ffae7e4aba5e1037098cf8fee23e5733892fde3c1.mp3" } ] } ], "prediction": "Amujpa gmu'ji'j p'tewe'l aq amujpa ni'n.", "reference": "Pe'l wesawa'l'g'p na p'teweio'q aq p'teweie'matesnu." }, { "id": "mic-sent-395db23fbf11dab4e5837e18:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The comet is very bright and has a long tail.", "output_text": "Pugtewit na gesaset aq pita'q ugsuguni.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The comet is very bright and has a long tail.", "mic_Latn": "Pugtewit na gesaset aq pita'q ugsuguni." }, "canonical_ref": "entries/p/pugtewit/pugtewit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c3e0b46153ff5161ad35", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pugtewit/pugtewit.html", "entry_url": "https://mikmaqonline.org/entries/p/pugtewit/pugtewit.html", "headword": "pugtewit", "example_index": 0, "raw_html_path": "raw/entries/ef86e644ed330f2a3d12ccc975e67975065f940472277da0d2f03985e9302990.html", "raw_html_sha256": "5d6ecfc64fe460a16e8f67ae33f797e78c37be55c1c63d5004f0d0f47b5862a0", "fetched_at": "2026-07-12T02:44:22.467Z", "recordings": [ { "recording_id": "5c0542fb841bc91e584cfaa9289c043a4d25724bbbbdab47b91916689b5dd7f1", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6f5/6f561713904d4be60201c02c2fdbc033f611756ad15ebf9e1b0c117e229bbbc7.mp3", "archive_relative_path": "raw/audio/6f5/6f561713904d4be60201c02c2fdbc033f611756ad15ebf9e1b0c117e229bbbc7.mp3" } ] } ], "prediction": "We'gwi'jg na we'gwigtug aq lugowaqanigtug.", "reference": "Pugtewit na gesaset aq pita'q ugsuguni." }, { "id": "mic-sent-398c537f94080d92732d83c4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I've been there four times to see that doctor.", "output_text": "Gi's ne'w wejiei apnmi'g na malpale'wit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I've been there four times to see that doctor.", "mic_Latn": "Gi's ne'w wejiei apnmi'g na malpale'wit." }, "canonical_ref": "entries/n/ne'w/ne'w.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-93f341f6152aa9e80bc9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ne'w/ne'w.html", "entry_url": "https://mikmaqonline.org/entries/n/ne'w/ne'w.html", "headword": "ne'w", "example_index": 0, "raw_html_path": "raw/entries/8fc64fa9bc2c9b99eae93dbc8f736cb72da18ee4d3a8ffc1998cadc0e1b702b2.html", "raw_html_sha256": "dd97fe199d8ea6d8d048d22cf9892c133338818c599cbf0a8338fb7a6acb7101", "fetched_at": "2026-07-12T02:42:26.277Z", "recordings": [ { "recording_id": "debf0b291e880c396476c686e0f8e0e55aed8e859bd7837101dfcfb135767ec7", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/83d/83d10c2878b4c076551741546e31145be4df5405bc7c3aaa511dadbc740a2aa8.mp3", "archive_relative_path": "raw/audio/83d/83d10c2878b4c076551741546e31145be4df5405bc7c3aaa511dadbc740a2aa8.mp3" } ] } ], "prediction": "Gi's gi's nige' gi'l na lpa'tuej.", "reference": "Gi's ne'w wejiei apnmi'g na malpale'wit." }, { "id": "mic-sent-3bca1dc9f09a5eb512674fcb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's taking him/her a long time to spread out the table cloth.", "output_text": "Pegijisiplega'toq na pata'utiawegn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's taking him/her a long time to spread out the table cloth.", "mic_Latn": "Pegijisiplega'toq na pata'utiawegn." }, "canonical_ref": "entries/s/sipelega'toq/sipelega'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-106080b3bc9c045e7d5a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sipelega'toq/sipelega'toq.html", "entry_url": "https://mikmaqonline.org/entries/s/sipelega'toq/sipelega'toq.html", "headword": "sipelega'toq", "example_index": 0, "raw_html_path": "raw/entries/4d1ffd99200c5a3571375f2a7b7de4978a9503c382b34c9185d91d5b284b703d.html", "raw_html_sha256": "e7769e7d1174ecfb7b7ac538e7862e65f86f99c64ae93f4bbd5ea89a2192b83e", "fetched_at": "2026-07-12T02:45:04.565Z", "recordings": [ { "recording_id": "cdde2b330bcff121c22693d6574312401bc45af191ddacb7950eb57f17a39323", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/381/3816b26a1cfe8df1b4746dbf552682980368630602c04900e0f3187a8a98502c.mp3", "archive_relative_path": "raw/audio/381/3816b26a1cfe8df1b4746dbf552682980368630602c04900e0f3187a8a98502c.mp3" } ] } ], "prediction": "Pugwelg ta'n tujiw etlmisga'latl ugtaqanigtug.", "reference": "Pegijisiplega'toq na pata'utiawegn." }, { "id": "mic-sent-3c68ad9434139e19164a9181:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she likes the look of my shirt that was given to me.", "output_text": "Welamatl ntatlaiml ta'n gisignmuimg'pnn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she likes the look of my shirt that was given to me.", "mic_Latn": "Welamatl ntatlaiml ta'n gisignmuimg'pnn." }, "canonical_ref": "entries/w/welamatl/welamatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-74abb5e52c1364e532a2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/welamatl/welamatl.html", "entry_url": "https://mikmaqonline.org/entries/w/welamatl/welamatl.html", "headword": "welamatl", "example_index": 0, "raw_html_path": "raw/entries/b29d76f12f8960f0feb05d37d8d048864198063e266f6172acee3d481176fc13.html", "raw_html_sha256": "02781ac261650869553d90e47189e82765432da2c74630f26ef9812f50b81201", "fetched_at": "2026-07-12T02:46:57.353Z", "recordings": [ { "recording_id": "2a428e2e38ab8ccdebece5bb34e63c08d08489f8ebe6958cfe617af41b3cc6a3", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fe5/fe5107438eaaceada6ecb3af981b03b2a2cfc07a40daf595d8bb103f58bfdf1f.mp3", "archive_relative_path": "raw/audio/fe5/fe5107438eaaceada6ecb3af981b03b2a2cfc07a40daf595d8bb103f58bfdf1f.mp3" } ] } ], "prediction": "We'gwi'g na ntmu'j gmu'ji'j gesatg.", "reference": "Welamatl ntatlaiml ta'n gisignmuimg'pnn." }, { "id": "mic-sent-3c86e88f9e60877ac80f73a6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Those are nice looking mittens on the one wearing mittens.", "output_text": "Welpiniji na ugtpijaqang ala alpijaqana'q.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Those are nice looking mittens on the one wearing mittens.", "mic_Latn": "Welpiniji na ugtpijaqang ala alpijaqana'q." }, "canonical_ref": "entries/p/pijjaqana'q/pijjaqana'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-59c101f55ad0fd278425", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pijjaqana'q/pijjaqana'q.html", "entry_url": "https://mikmaqonline.org/entries/p/pijjaqana'q/pijjaqana'q.html", "headword": "pijjaqana'q", "example_index": 0, "raw_html_path": "raw/entries/ac3d4d37e29e6b81f44af2268ec12492771d2688d8eb2c7e57213a52d07e8afa.html", "raw_html_sha256": "e76fa52422e747c4df349c0bae4a8f26c8bd7f9e02ff11872a1864b7f26e1453", "fetched_at": "2026-07-12T02:43:57.037Z", "recordings": [ { "recording_id": "931d1dfcba3665de3e5d976dc5852a7a28030a2a47465aa2a7366d454d80a126", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0e6/0e66ad646f846d73c36803bcca2c7c7aa37ac3c4751c2c6f1faa8957c959a247.mp3", "archive_relative_path": "raw/audio/0e6/0e66ad646f846d73c36803bcca2c7c7aa37ac3c4751c2c6f1faa8957c959a247.mp3" } ] } ], "prediction": "We'gwi'g na gmu'ji'j ta'n tujiw nugu' negm.", "reference": "Welpiniji na ugtpijaqang ala alpijaqana'q." }, { "id": "mic-sent-3cd2374a440e189dd397b31e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The boy is hanging over the edge of the cliff.", "output_text": "Lpa'tuj wesawa't paqse'gigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The boy is hanging over the edge of the cliff.", "mic_Latn": "Lpa'tuj wesawa't paqse'gigtug." }, "canonical_ref": "entries/w/wesawa't/wesawa't.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d6a33e36f26f70dd4491", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wesawa't/wesawa't.html", "entry_url": "https://mikmaqonline.org/entries/w/wesawa't/wesawa't.html", "headword": "wesawa't", "example_index": 0, "raw_html_path": "raw/entries/9e54a1f6ca3971089f3239af100cf3591579ca8a441a4b22e2e28a8a920d3954.html", "raw_html_sha256": "0eeeb9c1d08fc72e2e6a796de5183d97c47a650e81341223e960f8dbd01a0be9", "fetched_at": "2026-07-12T02:47:16.153Z", "recordings": [ { "recording_id": "72b18ebe885d6da2630cea3ea2d067f05f47928ccb3be3bc11428586a485e49b", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/387/38768fe008691a3448a5d733fd79f1153bb68ba0c051b7d0eafd1c70132f8a84.mp3", "archive_relative_path": "raw/audio/387/38768fe008691a3448a5d733fd79f1153bb68ba0c051b7d0eafd1c70132f8a84.mp3" } ] } ], "prediction": "Lpa'tu'ji'j etlmisga'sit.", "reference": "Lpa'tuj wesawa't paqse'gigtug." }, { "id": "mic-sent-3d124b5c380bcd9cc91d522e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little girl shows her doll, and says \"it's new\".", "output_text": "E'pite'ji'j neia'latl ugtapsute'gann, aq teluet \"pilei\".", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little girl shows her doll, and says \"it's new\".", "mic_Latn": "E'pite'ji'j neia'latl ugtapsute'gann, aq teluet \"pilei\"." }, "canonical_ref": "entries/n/neia'latl/neia'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b55e66e8dfe4906b02b1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/neia'latl/neia'latl.html", "entry_url": "https://mikmaqonline.org/entries/n/neia'latl/neia'latl.html", "headword": "neia'latl", "example_index": 0, "raw_html_path": "raw/entries/aaf8f3ed1a3fa03de285359adfe02988d716ace760164f513faadad9b6f22cb1.html", "raw_html_sha256": "b273855bb94b410b254c43fa7c9aafffd21ce07ddfbf1549599c05f5723d11b8", "fetched_at": "2026-07-12T02:42:16.508Z", "recordings": [ { "recording_id": "55b8dd85316d5388fb6d280b64076f50ad3334eed4e7071b78e31b0454f416ac", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a7b/a7b9eb2cc9590f4a473ba01923e6c4ec2a027213e1ea375da083e7481445a3fd.mp3", "archive_relative_path": "raw/audio/a7b/a7b9eb2cc9590f4a473ba01923e6c4ec2a027213e1ea375da083e7481445a3fd.mp3" } ] } ], "prediction": "E'pite'ji'j gesatg ugta'latl ugjitl, aq telitl \"newtig\".", "reference": "E'pite'ji'j neia'latl ugtapsute'gann, aq teluet \"pilei\"." }, { "id": "mic-sent-3d455c62d7a94b9d7433db3c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I think I remember the mother of that person from down the coast.", "output_text": "Telte'tm migwite'tmaqal uggwitl na papge'gewa'j.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I think I remember the mother of that person from down the coast.", "mic_Latn": "Telte'tm migwite'tmaqal uggwitl na papge'gewa'j." }, "canonical_ref": "entries/p/papge'gewa'j/papge'gewa'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-116496b91428f2b7163f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/papge'gewa'j/papge'gewa'j.html", "entry_url": "https://mikmaqonline.org/entries/p/papge'gewa'j/papge'gewa'j.html", "headword": "papge'gewa'j", "example_index": 0, "raw_html_path": "raw/entries/173fd4a5e8983603ddb38ada4759ac7c12bd168c42d14a7ce5353d2d5669f88a.html", "raw_html_sha256": "774d62d83fe889476c51f10baac5325708e8636c15079888f04110c50335d69a", "fetched_at": "2026-07-12T02:43:08.601Z", "recordings": [ { "recording_id": "270d68aeeda1957f8d333cf675f33df2f359840110fc3cef3648e85ccdae8f66", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/715/7150760fa2cf9e3f080b7d809e636e740545ae7a9503dc0d3294d8fe42b60180.mp3", "archive_relative_path": "raw/audio/715/7150760fa2cf9e3f080b7d809e636e740545ae7a9503dc0d3294d8fe42b60180.mp3" } ] } ], "prediction": "Telte's'g ni'n goqwei na ji'nm na gmu'j.", "reference": "Telte'tm migwite'tmaqal uggwitl na papge'gewa'j." }, { "id": "mic-sent-3db64bcb2ae73e495f9df785:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Tom shoes his horse.", "output_text": "Tuma mgumie'jo'tlatl ugtue'ml.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Tom shoes his horse.", "mic_Latn": "Tuma mgumie'jo'tlatl ugtue'ml." }, "canonical_ref": "entries/m/mgumie'jo'tlatl/mgumie'jo'tlatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-69150213a83a7940bda1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mgumie'jo'tlatl/mgumie'jo'tlatl.html", "entry_url": "https://mikmaqonline.org/entries/m/mgumie'jo'tlatl/mgumie'jo'tlatl.html", "headword": "mgumie'jo'tlatl", "example_index": 0, "raw_html_path": "raw/entries/e9962c5d3b86b99fce0b3c0aa4c9013962adc9ef27789909ce07b866b86b5e0f.html", "raw_html_sha256": "08266e6bf7e2cdf0e67c8e553282f9a915c16cdf93503e1299059635e0d7aff3", "fetched_at": "2026-07-12T02:41:31.823Z", "recordings": [ { "recording_id": "5098c3466cd6d0b83057c385598d3371901277d240816ccc669629b53bf441df", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/28b/28b0e95a6f21e9b28e03f2852181d99bde02f89fdb5469b169843b1aaf2c131c.mp3", "archive_relative_path": "raw/audio/28b/28b0e95a6f21e9b28e03f2852181d99bde02f89fdb5469b169843b1aaf2c131c.mp3" } ] } ], "prediction": "Tuma gesatg ugti'l.", "reference": "Tuma mgumie'jo'tlatl ugtue'ml." }, { "id": "mic-sent-3e20d856742c1bcec4203f8e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "If he/she can help it, he/she will have passed it before the end of this year.", "output_text": "Gisipgwatoq pmg'tew gesgmnaq ula newtipunqeg gaqianug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "If he/she can help it, he/she will have passed it before the end of this year.", "mic_Latn": "Gisipgwatoq pmg'tew gesgmnaq ula newtipunqeg gaqianug." }, "canonical_ref": "entries/p/pemg'g/pemg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-55bce18c051aa290283d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemg'g/pemg'g.html", "entry_url": "https://mikmaqonline.org/entries/p/pemg'g/pemg'g.html", "headword": "pemg'g", "example_index": 0, "raw_html_path": "raw/entries/5ee99980a4e62705fa98c420c3d7b257950735a10005a7ce19623b56113d4525.html", "raw_html_sha256": "a358efa5df4b0578cf3493022a8628c7788c721478d3e53c1072bd1ad975720d", "fetched_at": "2026-07-12T02:43:31.103Z", "recordings": [ { "recording_id": "ea51c0fec4fcec74c7a77233e398b080ae38ad2fbe3e712a1a0e5a03df4cd6ef", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/410/410bfaafc9ccbf3117d7edfb0bc8a87aeb090562089511d80ca8c8ab13b1c953.mp3", "archive_relative_path": "raw/audio/410/410bfaafc9ccbf3117d7edfb0bc8a87aeb090562089511d80ca8c8ab13b1c953.mp3" } ] } ], "prediction": "Ge' negm na'te'l, gesgmnaq nige' newte'g ula te's'g.", "reference": "Gisipgwatoq pmg'tew gesgmnaq ula newtipunqeg gaqianug." }, { "id": "mic-sent-3e412f5176464f8b01ce70b3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The dog lies facing away near the fire.", "output_text": "Nmu'j enmigjesing gigji'w pugtewigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The dog lies facing away near the fire.", "mic_Latn": "Nmu'j enmigjesing gigji'w pugtewigtug." }, "canonical_ref": "entries/e/enmigjesing/enmigjesing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-49a1f30194ffe3a89128", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/enmigjesing/enmigjesing.html", "entry_url": "https://mikmaqonline.org/entries/e/enmigjesing/enmigjesing.html", "headword": "enmigjesing", "example_index": 0, "raw_html_path": "raw/entries/7004eb2045a0b4b7153f0937f9d38a5d13b53db78f763ecc2fdb917145c1bd74.html", "raw_html_sha256": "4a986e621795d74f86809816af2c0b19cadcea9db721238e882bd5fde090bc97", "fetched_at": "2026-07-12T02:38:02.389Z", "recordings": [ { "recording_id": "1e18972bd8d5a66110a6c273aa30af4be97302ece430e7f064053a64e725e019", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/76b/76b4f0fd5ffc5b3e3176d3e0487da074513c46bf28920c6080cdc5ee8552ae89.mp3", "archive_relative_path": "raw/audio/76b/76b4f0fd5ffc5b3e3176d3e0487da074513c46bf28920c6080cdc5ee8552ae89.mp3" } ] } ], "prediction": "Nmu'ji'j gesatg ta'n te'sipow.", "reference": "Nmu'j enmigjesing gigji'w pugtewigtug." }, { "id": "mic-sent-3eb1b6b64691b701bdd832c9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she often belittles his/her friend.", "output_text": "Witapal gaqi'sg ejaqjematl", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she often belittles his/her friend.", "mic_Latn": "Witapal gaqi'sg ejaqjematl" }, "canonical_ref": "entries/e/ejaqjematl/ejaqjematl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e36b873ccc3550a18192", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/ejaqjematl/ejaqjematl.html", "entry_url": "https://mikmaqonline.org/entries/e/ejaqjematl/ejaqjematl.html", "headword": "ejaqjematl", "example_index": 0, "raw_html_path": "raw/entries/48a86ca25c8507caa01bc852d8e98212a4376c5f89a1bf430fcd71d8af623420.html", "raw_html_sha256": "a867c7722cad0d818015d58f3bf2e038e99fe540cd606438a37b54a7baae3b84", "fetched_at": "2026-07-12T02:37:32.905Z", "recordings": [ { "recording_id": "070fd11a24ddf939415e737e30ac6ced2aee3e1b222bb2f78e15b03c50164995", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/80b/80b6e5113956d6c17d77414fcfc83b67cf521afc7f6d3b1d34248b89c21d32a1.mp3", "archive_relative_path": "raw/audio/80b/80b6e5113956d6c17d77414fcfc83b67cf521afc7f6d3b1d34248b89c21d32a1.mp3" } ] } ], "prediction": "Te's gaqamitl witapal.", "reference": "Witapal gaqi'sg ejaqjematl" }, { "id": "mic-sent-3ebe8924ef62a17e42c97746:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she laughed so hard he/she fell backwards.", "output_text": "Tetujimamunelmit lpa aputasgiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she laughed so hard he/she fell backwards.", "mic_Latn": "Tetujimamunelmit lpa aputasgiet." }, "canonical_ref": "entries/a/aputasgiet/aputasgiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a3327bcfb980f7ba25c5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/aputasgiet/aputasgiet.html", "entry_url": "https://mikmaqonline.org/entries/a/aputasgiet/aputasgiet.html", "headword": "aputasgiet", "example_index": 0, "raw_html_path": "raw/entries/2d760da30755c0920987be63f89854d51557d5ae83a6e64cf60ea0ae9c123530.html", "raw_html_sha256": "7e38169b7616a8d543bfd56cc47ae216291e9afbe128854c909892efff661e9c", "fetched_at": "2026-07-12T02:37:15.263Z", "recordings": [ { "recording_id": "f7ad354e1cc1105aab8feec7fb6c7b5e8a78c59df055352e5124f077289a50c4", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/030/030967e51ed6f1e5df17d32dc39f6b3a4302d59ea8f9a40a07980def473d634d.mp3", "archive_relative_path": "raw/audio/030/030967e51ed6f1e5df17d32dc39f6b3a4302d59ea8f9a40a07980def473d634d.mp3" } ] } ], "prediction": "Tetuji'jg te'sipi'g.", "reference": "Tetujimamunelmit lpa aputasgiet." }, { "id": "mic-sent-3f42d57c85263fe6254a9579:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary is often going around in a hurry.", "output_text": "Mali na negm pusgialinenaqe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary is often going around in a hurry.", "mic_Latn": "Mali na negm pusgialinenaqe'g." }, "canonical_ref": "entries/n/nenaqe'g/nenaqe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-69956b35896f5e12a848", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nenaqe'g/nenaqe'g.html", "entry_url": "https://mikmaqonline.org/entries/n/nenaqe'g/nenaqe'g.html", "headword": "nenaqe'g", "example_index": 0, "raw_html_path": "raw/entries/56d7f71164f94d39600c2836ef30a8c61ace72a428ec7afe15b689aded3bea83.html", "raw_html_sha256": "367e30fb5c6eb912e6a0a4bbed74c124cf3aa4acaba5bfb9c678a7710a46bf0b", "fetched_at": "2026-07-12T02:42:18.530Z", "recordings": [ { "recording_id": "77ab4c7161dc5034e52d923023eccd91977125424506f42f756b55e17b4e07a0", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c3a/c3ad898729df63421c0e1187107b1e04f41cbbdfb12ee7882f0436c5264a71ef.mp3", "archive_relative_path": "raw/audio/c3a/c3ad898729df63421c0e1187107b1e04f41cbbdfb12ee7882f0436c5264a71ef.mp3" } ] } ], "prediction": "Mali te's'g na gisijig.", "reference": "Mali na negm pusgialinenaqe'g." }, { "id": "mic-sent-3fa825bba3ea83af649212b3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The mediation is on going this morning.", "output_text": "Petqa'matimg wesgowa's'g ula egsitpu'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The mediation is on going this morning.", "mic_Latn": "Petqa'matimg wesgowa's'g ula egsitpu'g." }, "canonical_ref": "entries/p/petqa'matimg/petqa'matimg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-aa239a7cae3633850de7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/petqa'matimg/petqa'matimg.html", "entry_url": "https://mikmaqonline.org/entries/p/petqa'matimg/petqa'matimg.html", "headword": "petqa'matimg", "example_index": 0, "raw_html_path": "raw/entries/ba9b9247b6bd89b1c608d791021f6ada80f7fa07bfedc588535d6ee3f1ee69f7.html", "raw_html_sha256": "f0a5a90b054af97a2054784f7f16a1a265ffdf156982ab9420770c17781a3221", "fetched_at": "2026-07-12T02:43:48.901Z", "recordings": [ { "recording_id": "2fdd7823f445754485d48fb24645236adc200b8236873175377a9968efd5ca55", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9fa/9fafb827755d9fe50533be9963ca1ae312022f07c1b398d7bf530726ccd32e65.mp3", "archive_relative_path": "raw/audio/9fa/9fafb827755d9fe50533be9963ca1ae312022f07c1b398d7bf530726ccd32e65.mp3" } ] } ], "prediction": "Sapo'gwe'g etlmisga'toq ula egsitpu'g.", "reference": "Petqa'matimg wesgowa's'g ula egsitpu'g." }, { "id": "mic-sent-3ff14d808d23ca5229ef06f8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I going to strain my vocal cords if I keep yelling.", "output_text": "Pestaqa'la's nsitunapi'g ugsamsesgweian.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I going to strain my vocal cords if I keep yelling.", "mic_Latn": "Pestaqa'la's nsitunapi'g ugsamsesgweian." }, "canonical_ref": "entries/u/ugsitunapi'l/ugsitunapi'l.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bc6948e4bcfef439bda0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugsitunapi'l/ugsitunapi'l.html", "entry_url": "https://mikmaqonline.org/entries/u/ugsitunapi'l/ugsitunapi'l.html", "headword": "ugsitunapi'l", "example_index": 0, "raw_html_path": "raw/entries/33273378a38750bc0dbf83cda6bd2a071f20ba40bb65240635f06526d90321d2.html", "raw_html_sha256": "03ece634b8f2d84e50c47f02440e0e82aef90c5e375b3387124b90ef6f14c768", "fetched_at": "2026-07-12T02:46:15.535Z", "recordings": [ { "recording_id": "b2cafd81b003ff5afba29445bc84c66f462db42f6138b23217128b1de1ca7363", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bc6/bc651f5c7931b3eb5a778b72357c065f65743dde38034ec58f1cfa31b3ed7e57.mp3", "archive_relative_path": "raw/audio/bc6/bc651f5c7931b3eb5a778b72357c065f65743dde38034ec58f1cfa31b3ed7e57.mp3" } ] } ], "prediction": "Pugwelga'toq nugu' ni'n telgwi'g.", "reference": "Pestaqa'la's nsitunapi'g ugsamsesgweian." }, { "id": "mic-sent-4009a9ae2ba3455f83373995:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Yes, sometimes they are timid, but not everyday.", "output_text": "E'e, jijuaqa nesawa'utijig, gatu mu te'sigisg'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Yes, sometimes they are timid, but not everyday.", "mic_Latn": "E'e, jijuaqa nesawa'utijig, gatu mu te'sigisg'g." }, "canonical_ref": "entries/n/nesawet/nesawet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2f35cba0754a464de214", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nesawet/nesawet.html", "entry_url": "https://mikmaqonline.org/entries/n/nesawet/nesawet.html", "headword": "nesawet", "example_index": 0, "raw_html_path": "raw/entries/117942ba74d43f7610b986f72d4589aff1db08c1ae668393e8eb7245c8e4055a.html", "raw_html_sha256": "06505bb05afe4fb913c89aa2bcba86079ac67d4c159d942eeb3fddbbd9dabd04", "fetched_at": "2026-07-12T02:42:21.785Z", "recordings": [ { "recording_id": "17c9b4db7f7a2773e1faf313b3241ae9b2e5a793df377e2367c7a78a04164d9f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/472/4729292ce5390adc669d65c53af0b297d4f2062eadd80185eb3f874990d394df.mp3", "archive_relative_path": "raw/audio/472/4729292ce5390adc669d65c53af0b297d4f2062eadd80185eb3f874990d394df.mp3" } ] } ], "prediction": "E'e, te's'g na'te'ji'jig, gatu mu te'sipu'g.", "reference": "E'e, jijuaqa nesawa'utijig, gatu mu te'sigisg'g." }, { "id": "mic-sent-402d78ba98af20e206add219:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Tomorrow morning they are going up to the woods to hunt.", "output_text": "Egsitpu'nug so'qwita'jig najigtantaqatijig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Tomorrow morning they are going up to the woods to hunt.", "mic_Latn": "Egsitpu'nug so'qwita'jig najigtantaqatijig." }, "canonical_ref": "entries/n/nutanteget/nutanteget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-751e9c002d51b5fa5ee5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nutanteget/nutanteget.html", "entry_url": "https://mikmaqonline.org/entries/n/nutanteget/nutanteget.html", "headword": "nutanteget", "example_index": 0, "raw_html_path": "raw/entries/c9b34750a28a3a87b533fb1c309bca8b838540e3559d064ed50e5e8c47f8a836.html", "raw_html_sha256": "a6818f45f81106486cc8af2817b20be539430fde86043e2e2b3a0b92598f23b4", "fetched_at": "2026-07-12T02:42:55.023Z", "recordings": [ { "recording_id": "781c8c0a4ef4c7ec6112f4d7e521a8864d477d5f40d932428db8bd9b4c8f83f8", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e93/e9338c7aec788dc379665118b6adccf3116300a1c3e08737bc43225ca9a71462.mp3", "archive_relative_path": "raw/audio/e93/e9338c7aec788dc379665118b6adccf3116300a1c3e08737bc43225ca9a71462.mp3" } ] } ], "prediction": "Sapo'siegsitpu'g na'te's'g'p'tijig.", "reference": "Egsitpu'nug so'qwita'jig najigtantaqatijig." }, { "id": "mic-sent-4044997ddd02494f40ca999b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Bear grease is used as medicine.", "output_text": "Mui'nu'mi wijei teluegeg st'ge npisun.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Bear grease is used as medicine.", "mic_Latn": "Mui'nu'mi wijei teluegeg st'ge npisun." }, "canonical_ref": "entries/t/teluegeg/teluegeg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-deaaba785f099d96a467", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/teluegeg/teluegeg.html", "entry_url": "https://mikmaqonline.org/entries/t/teluegeg/teluegeg.html", "headword": "teluegeg", "example_index": 0, "raw_html_path": "raw/entries/2a4f1dcfceab3af06531f87cfdc9cbb8edba6aab0437f3d42c5ef2b691e53727.html", "raw_html_sha256": "1a09781011c19305556c08129117add7cbbe35f2fa3f0d67c7f933157beb6967", "fetched_at": "2026-07-12T02:45:35.311Z", "recordings": [ { "recording_id": "80183f77a747d3097e21ccd4fbcd2bd29fa3fa7004ce366bb8705f865a9c7c69", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6fd/6fd75ab9135deed64ab2ce23b44b633e2a387db65f1c8d63066760ae9b98e776.mp3", "archive_relative_path": "raw/audio/6fd/6fd75ab9135deed64ab2ce23b44b633e2a387db65f1c8d63066760ae9b98e776.mp3" } ] } ], "prediction": "Nmu'ji'j na ugjit ugjit nugu' ugjit.", "reference": "Mui'nu'mi wijei teluegeg st'ge npisun." }, { "id": "mic-sent-40494e4acff613251f6f99e4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Honestly is that true?", "output_text": "Meluijoqo teliaq na?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Honestly is that true?", "mic_Latn": "Meluijoqo teliaq na?" }, "canonical_ref": "entries/m/meluijoqo/meluijoqo.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a6fcad74ab1be98d72c9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/meluijoqo/meluijoqo.html", "entry_url": "https://mikmaqonline.org/entries/m/meluijoqo/meluijoqo.html", "headword": "meluijoqo", "example_index": 0, "raw_html_path": "raw/entries/1a5268c63c5581cfbebfed8ed9597e38a0f637e55237b5727fcc3456f818ecf0.html", "raw_html_sha256": "5716b4f95790bd4b0cc56fa0df8d8ba97dd9583cdaf6007a042916c35214a1a3", "fetched_at": "2026-07-12T02:41:13.287Z", "recordings": [ { "recording_id": "79838195c51c5d46be96cd7a0b2d1ed07d0a397ccc26a390bc9ff17f47ba0d8d", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7da/7da8b2a32af12ee01eeb71ad0f51cb42157e386ef895953c0e2ef7f6b87d0ff1.mp3", "archive_relative_path": "raw/audio/7da/7da8b2a32af12ee01eeb71ad0f51cb42157e386ef895953c0e2ef7f6b87d0ff1.mp3" } ] } ], "prediction": "Gi's goqwei na?", "reference": "Meluijoqo teliaq na?" }, { "id": "mic-sent-408e86646c54df3bfeb261ee:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My dear, where are you going?", "output_text": "Oqoti, tami elien?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My dear, where are you going?", "mic_Latn": "Oqoti, tami elien?" }, "canonical_ref": "entries/o/oqoti/oqoti.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0b0f7282e4a2fca612b5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/o/oqoti/oqoti.html", "entry_url": "https://mikmaqonline.org/entries/o/oqoti/oqoti.html", "headword": "oqoti", "example_index": 0, "raw_html_path": "raw/entries/9a01cc418c38a9d7c84cf0066f0d1b965bdace4c4f9cc15ad212d3e121c0175b.html", "raw_html_sha256": "8445aca905a0508ce4eeb8f099f93865db294cfdc4166a2717da2a1934204b23", "fetched_at": "2026-07-12T02:43:02.573Z", "recordings": [ { "recording_id": "6392350c4280776730cdd7fff6af19c07fe8226b7463283f443fa7a3e90b4506", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/564/564eae74a13dca8b4fa059aeb25ceb16192e859c04382d3f2216429dde37d709.mp3", "archive_relative_path": "raw/audio/564/564eae74a13dca8b4fa059aeb25ceb16192e859c04382d3f2216429dde37d709.mp3" } ] } ], "prediction": "Gisigu, ta'n goqwei?", "reference": "Oqoti, tami elien?" }, { "id": "mic-sent-40dd99fb08e37266ccc65968:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Pierre just killed a moose yesterday.", "output_text": "Pie'l pas'g gis sigteluatl tia'mul ulagu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Pierre just killed a moose yesterday.", "mic_Latn": "Pie'l pas'g gis sigteluatl tia'mul ulagu." }, "canonical_ref": "entries/s/sigteluatl/sigteluatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7d8aff737d7d63126eb8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sigteluatl/sigteluatl.html", "entry_url": "https://mikmaqonline.org/entries/s/sigteluatl/sigteluatl.html", "headword": "sigteluatl", "example_index": 0, "raw_html_path": "raw/entries/e0fbeb870abbf6e664ae34c61fc87a1581960cac4372924dda09adf053071bc0.html", "raw_html_sha256": "aceee786e5e055e3b4628a5567c726ae814eb96dbb8ff9296ea40826abf6b6b8", "fetched_at": "2026-07-12T02:45:01.142Z", "recordings": [ { "recording_id": "385a6752a488627ea127e24cc7915035154bc0426657ec9806c23b5f2c4d6009", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/032/03280b9168ab5378de7503852211bdbfd038582866678efc771f1d689d5e310b.mp3", "archive_relative_path": "raw/audio/032/03280b9168ab5378de7503852211bdbfd038582866678efc771f1d689d5e310b.mp3" } ] } ], "prediction": "Pie'l pas'g gesatg ulagu.", "reference": "Pie'l pas'g gis sigteluatl tia'mul ulagu." }, { "id": "mic-sent-4116e46b9107e130103a23a7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "We are feeling proud of our accomplishments.", "output_text": "Gi'nujultieg ugjit ta'n tel gisi ullugutieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "We are feeling proud of our accomplishments.", "mic_Latn": "Gi'nujultieg ugjit ta'n tel gisi ullugutieg." }, "canonical_ref": "entries/g/gi'nujing/gi'nujing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-39cc7ba8dfbb10fe08b3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gi'nujing/gi'nujing.html", "entry_url": "https://mikmaqonline.org/entries/g/gi'nujing/gi'nujing.html", "headword": "gi'nujing", "example_index": 0, "raw_html_path": "raw/entries/1cda6b59c27709a25c86589b36e0b495da3d0a6bb6693c674b3a77e7828b5800.html", "raw_html_sha256": "c91bae5eced9fcc6ba51f3d967e0a3a02d5bd8615e4cd69334d1c8e523597544", "fetched_at": "2026-07-12T02:39:35.251Z", "recordings": [ { "recording_id": "0915e87e440dd760ddc64b7bd6bfd451ece6eac90f0af3d5fc13fe03b4d652f6", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f37/f37974d9e6221e88de95eb947ae7288d575cc9939798a67efd74ab9518ecf257.mp3", "archive_relative_path": "raw/audio/f37/f37974d9e6221e88de95eb947ae7288d575cc9939798a67efd74ab9518ecf257.mp3" } ] } ], "prediction": "We'gwi'gig ta'n te'sipowtimg.", "reference": "Gi'nujultieg ugjit ta'n tel gisi ullugutieg." }, { "id": "mic-sent-41dd49a834c41968b7ddce75:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Seaweed floats.", "output_text": "Paqo'si alqo'qweg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Seaweed floats.", "mic_Latn": "Paqo'si alqo'qweg." }, "canonical_ref": "entries/a/alqo'qweg/alqo'qweg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-fde584c920f9d1a88646", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/alqo'qweg/alqo'qweg.html", "entry_url": "https://mikmaqonline.org/entries/a/alqo'qweg/alqo'qweg.html", "headword": "alqo'qweg", "example_index": 0, "raw_html_path": "raw/entries/12c44e6a01427062496d594c55538f415cf1f3c1ddbcb383b27e57b142af1f87.html", "raw_html_sha256": "31c81691c59975eb3a9532d00168783a6d19802ddfbe2accfc0b7e166666f476", "fetched_at": "2026-07-12T02:36:42.942Z", "recordings": [ { "recording_id": "ef237fa4eca7726ad3ee4b09b5de3a5cd30dda9de817018bb7b7461ee057ea2c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b73/b738315ef6d839341edfac3d925419179ed05d7e7a4d3bb5c8f1a0934dbf546c.mp3", "archive_relative_path": "raw/audio/b73/b738315ef6d839341edfac3d925419179ed05d7e7a4d3bb5c8f1a0934dbf546c.mp3" } ] } ], "prediction": "Pugji'j gesatg.", "reference": "Paqo'si alqo'qweg." }, { "id": "mic-sent-4274bfd1ff8e1b6ae2218161:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Today I will try not to speak for too long.", "output_text": "Ugjo'tes gisgug mu ugsamipgitewo'gwen.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Today I will try not to speak for too long.", "mic_Latn": "Ugjo'tes gisgug mu ugsamipgitewo'gwen." }, "canonical_ref": "entries/p/pegitewo'gwet/pegitewo'gwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-784b39c6f2482452cbc8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pegitewo'gwet/pegitewo'gwet.html", "entry_url": "https://mikmaqonline.org/entries/p/pegitewo'gwet/pegitewo'gwet.html", "headword": "pegitewo'gwet", "example_index": 0, "raw_html_path": "raw/entries/00151a4fbddd82f51dcbf59a4f41864cbec4a93df0f0b0613985778d91feafcc.html", "raw_html_sha256": "e262fb3f65ae8cbafc7811a0738e038c2a9b39523135e31506fd2cb07f2256bf", "fetched_at": "2026-07-12T02:43:21.758Z", "recordings": [ { "recording_id": "dd2ffca7ffe66f402fbe566cb66080e580f16cb8f3554d1f0d1887156a1c33dc", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/31c/31cc5ad1d99d211f4a8c2306d81c4b17397fd76b4404a3acc8b0a88a3df79b3d.mp3", "archive_relative_path": "raw/audio/31c/31cc5ad1d99d211f4a8c2306d81c4b17397fd76b4404a3acc8b0a88a3df79b3d.mp3" } ] } ], "prediction": "Gisgug nige' ma' nugu' mima'toq.", "reference": "Ugjo'tes gisgug mu ugsamipgitewo'gwen." }, { "id": "mic-sent-432d6d7cfbebed1466503a34:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My mother-in-law lives beside me.", "output_text": "Njugwi'ji'j wigit gmetug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My mother-in-law lives beside me.", "mic_Latn": "Njugwi'ji'j wigit gmetug." }, "canonical_ref": "entries/g/gmetug/gmetug.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-37e50dc65a86b2eb6b5e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gmetug/gmetug.html", "entry_url": "https://mikmaqonline.org/entries/g/gmetug/gmetug.html", "headword": "gmetug", "example_index": 0, "raw_html_path": "raw/entries/f9900c2c4cbc957c1b98ebf364c5682103f8a553f34a5f5d4448a703f63bf58e.html", "raw_html_sha256": "3d758fd438cc18ef5005603eb386f7b57e93d273755ea354d828e94680748d40", "fetched_at": "2026-07-12T02:39:51.630Z", "recordings": [ { "recording_id": "9d77ced5389e01a217334ef1547209ee35045f3f41db3c7154f69ddbf0a61462", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/546/5464cb2a14ff6aa3d6d1875ec516fe60fc5c5d60d0008e1f85d3d365c811119b.mp3", "archive_relative_path": "raw/audio/546/5464cb2a14ff6aa3d6d1875ec516fe60fc5c5d60d0008e1f85d3d365c811119b.mp3" } ] } ], "prediction": "Nuji'j na nugu' ni'n.", "reference": "Njugwi'ji'j wigit gmetug." }, { "id": "mic-sent-4359e5df8bc49fe9c4a09775:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I am the first one to work on this word.", "output_text": "Amgwesewa'jui lugwatmn (u)la glusuaqn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I am the first one to work on this word.", "mic_Latn": "Amgwesewa'jui lugwatmn (u)la glusuaqn." }, "canonical_ref": "entries/a/amgwesewa'j/amgwesewa'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d2094c6ea8eb806f5df3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amgwesewa'j/amgwesewa'j.html", "entry_url": "https://mikmaqonline.org/entries/a/amgwesewa'j/amgwesewa'j.html", "headword": "amgwesewa'j", "example_index": 0, "raw_html_path": "raw/entries/4e8abf7ca55f6669306824a41e00f72e8f376a566588fc9c5d308e4d82828989.html", "raw_html_sha256": "2a429fc4034a74f547062a34bb2905b65be8c81643819c983c5fcf19bd4db041", "fetched_at": "2026-07-12T02:36:50.378Z", "recordings": [ { "recording_id": "6ce06ebd8a7f5b2c044bf596ffd593089cbfca632ceb72cfe9fe2a1127acfef3", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a40/a40e3122bdca8d2cc0974860fd66949dcd3ea62a4f9706f918aec3d9bf25ff8b.mp3", "archive_relative_path": "raw/audio/a40/a40e3122bdca8d2cc0974860fd66949dcd3ea62a4f9706f918aec3d9bf25ff8b.mp3" } ] } ], "prediction": "Ni'n nige' newte'g ula wi'gatign.", "reference": "Amgwesewa'jui lugwatmn (u)la glusuaqn." }, { "id": "mic-sent-43ab840fe34974d9afe3711e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "How many yards will it take if I make pants?", "output_text": "Ta'sgl lape'lisl etug ugsua'tutal ltuan pita'qawe'l?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "How many yards will it take if I make pants?", "mic_Latn": "Ta'sgl lape'lisl etug ugsua'tutal ltuan pita'qawe'l?" }, "canonical_ref": "entries/l/lape'lis/lape'lis.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-62abbd27a54360386e5a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lape'lis/lape'lis.html", "entry_url": "https://mikmaqonline.org/entries/l/lape'lis/lape'lis.html", "headword": "lape'lis", "example_index": 0, "raw_html_path": "raw/entries/ba37bdd7e582ccc393255459350627018b8453a103f0b694773fdc1c394e6386.html", "raw_html_sha256": "ff49b50fb94356cb456f727231adc931cd809a2cdfd84a0cef65a2970467f9a1", "fetched_at": "2026-07-12T02:40:29.881Z", "recordings": [ { "recording_id": "30b9fa0d2b1a0d08240f5f00d5b623a08bee37d9e9035692998a9885056cf0b1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f0f/f0fb26072676a5a8c3551d3c3cd47313f9f7297f358e5e2577828cae7fb11d96.mp3", "archive_relative_path": "raw/audio/f0f/f0fb26072676a5a8c3551d3c3cd47313f9f7297f358e5e2577828cae7fb11d96.mp3" } ] } ], "prediction": "Ta'sijig ta'n te's'g na'te'l?", "reference": "Ta'sgl lape'lisl etug ugsua'tutal ltuan pita'qawe'l?" }, { "id": "mic-sent-44455abd9ec2e27747bd3fb5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she injured himself/herself there because it is slippery at his/her work.", "output_text": "Wejigsitesing muta sesupe'g ta'n etllugwej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she injured himself/herself there because it is slippery at his/her work.", "mic_Latn": "Wejigsitesing muta sesupe'g ta'n etllugwej." }, "canonical_ref": "entries/w/wejigsitesing/wejigsitesing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d4a75bc428aca5274c47", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejigsitesing/wejigsitesing.html", "entry_url": "https://mikmaqonline.org/entries/w/wejigsitesing/wejigsitesing.html", "headword": "wejigsitesing", "example_index": 0, "raw_html_path": "raw/entries/b295023937de29935d88b63ee393fafe5f74725f466e1f44345a401a4e7028d0.html", "raw_html_sha256": "709ac8470718d261e045155fc5dabd1216691f1ff0e5ba98c6b28a1800e3aa4d", "fetched_at": "2026-07-12T02:46:53.020Z", "recordings": [ { "recording_id": "e53849d2424af1f3aabcbb9d4718fb12406f6c50bc1401ca22fbce5676985abd", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5ee/5ee6fa63a31594cc7b793107445b24d8d90fb1a80f0b80171cf48b0416ceb2b8.mp3", "archive_relative_path": "raw/audio/5ee/5ee6fa63a31594cc7b793107445b24d8d90fb1a80f0b80171cf48b0416ceb2b8.mp3" } ] } ], "prediction": "Na'te'g na muta gesatg etlugowaqan ugjit ugjiw.", "reference": "Wejigsitesing muta sesupe'g ta'n etllugwej." }, { "id": "mic-sent-44821cabe57a74650b0b43b9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The old fella draws water from the well each morning.", "output_text": "Gisigu naqana'pet nqano'patigtug te'siegsitpu'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The old fella draws water from the well each morning.", "mic_Latn": "Gisigu naqana'pet nqano'patigtug te'siegsitpu'g." }, "canonical_ref": "entries/n/naqana'pet/naqana'pet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d042eb2c9d3be38e2f69", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/naqana'pet/naqana'pet.html", "entry_url": "https://mikmaqonline.org/entries/n/naqana'pet/naqana'pet.html", "headword": "naqana'pet", "example_index": 0, "raw_html_path": "raw/entries/0238d27df832911ae8d7beb55e202832b5fac0098503d2cc3f21b0f5a17887c7.html", "raw_html_sha256": "5cda9c8599529fd8c8e0ccecf27062ac6c31fcb228cec7c3a3b561566a1761b8", "fetched_at": "2026-07-12T02:42:02.632Z", "recordings": [ { "recording_id": "e1294cb63458fb1a720fb7ee79178e10a4046d7e95e6c5482a9eae53ff783755", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4ad/4ad611ba95ffa5bab6bbb6351d1213cbfe4e6502194cea2c53f3a9f36d9c8db3.mp3", "archive_relative_path": "raw/audio/4ad/4ad611ba95ffa5bab6bbb6351d1213cbfe4e6502194cea2c53f3a9f36d9c8db3.mp3" } ] } ], "prediction": "Gisigu'sgw gisgugsitpu'g te'siegsitpueg.", "reference": "Gisigu naqana'pet nqano'patigtug te'siegsitpu'g." }, { "id": "mic-sent-44c9d1e76b2d820f1e4e3617:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The old man is wearing out his hat.", "output_text": "Gisigu gaqg'g ugta'gusn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The old man is wearing out his hat.", "mic_Latn": "Gisigu gaqg'g ugta'gusn." }, "canonical_ref": "entries/g/gaqg'g/gaqg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2b0ca93112624768e14a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gaqg'g/gaqg'g.html", "entry_url": "https://mikmaqonline.org/entries/g/gaqg'g/gaqg'g.html", "headword": "gaqg'g", "example_index": 0, "raw_html_path": "raw/entries/ac55f67e7fe0b1fbd14dc8d37a1006022bdc9d1085d6c87e098ee4325b74cccd.html", "raw_html_sha256": "cf56dce842eaa54edff620553c0809c17ea281e5e08cd9bdbe50ea81fd2945cf", "fetched_at": "2026-07-12T02:38:40.391Z", "recordings": [ { "recording_id": "da562bffb8bc9fa75f9bf645b598b319340fe2c726ecb015d1f64463d7fdcbda", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/232/23234898a8f6ea4bdcc8b475dda068c3f49f274383027a5fe6ce0fed8b1f8b27.mp3", "archive_relative_path": "raw/audio/232/23234898a8f6ea4bdcc8b475dda068c3f49f274383027a5fe6ce0fed8b1f8b27.mp3" } ] } ], "prediction": "Gisigu e'pite'latl ugjitl.", "reference": "Gisigu gaqg'g ugta'gusn." }, { "id": "mic-sent-4677f4527eda89ea20d20601:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The rooster crows at daybreak.", "output_text": "Nape'w getu'g wejgwapniaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The rooster crows at daybreak.", "mic_Latn": "Nape'w getu'g wejgwapniaq." }, "canonical_ref": "entries/g/getu'g/getu'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-68e0d9f217c6c402f8b7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/getu'g/getu'g.html", "entry_url": "https://mikmaqonline.org/entries/g/getu'g/getu'g.html", "headword": "getu'g", "example_index": 0, "raw_html_path": "raw/entries/96f97966c4601ab2e72912df6340e119c46d7496517cb26df85150270020894a.html", "raw_html_sha256": "0d89fa75207a5d5d471ea0b93f2cacf3cefb30fc7438c934ead54b94da207b07", "fetched_at": "2026-07-12T02:39:24.588Z", "recordings": [ { "recording_id": "b5ded1fcd1d3f2dc709ffa8637a0f21b7193f906f779d24d6acdc0759020cc9a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d2e/d2e63c05eedd161f1ed0752332edf455f34633d14d9286ef78f7570423a87f1a.mp3", "archive_relative_path": "raw/audio/d2e/d2e63c05eedd161f1ed0752332edf455f34633d14d9286ef78f7570423a87f1a.mp3" } ] } ], "prediction": "Pugji'j etlmisga'sit ta'n te's'g.", "reference": "Nape'w getu'g wejgwapniaq." }, { "id": "mic-sent-46b73d1ec8050298825dadfe:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she beat him/her quickly at checkers.", "output_text": "We'gwijaqalta'tl atnaqanigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she beat him/her quickly at checkers.", "mic_Latn": "We'gwijaqalta'tl atnaqanigtug." }, "canonical_ref": "entries/j/jaqalta'tl/jaqalta'tl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3de6da6cea89bbdbb068", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jaqalta'tl/jaqalta'tl.html", "entry_url": "https://mikmaqonline.org/entries/j/jaqalta'tl/jaqalta'tl.html", "headword": "jaqalta'tl", "example_index": 0, "raw_html_path": "raw/entries/092cfa2fba342c35cef1c7ee4f948ce0e21f044623ba62eebb4914735a0f0553.html", "raw_html_sha256": "ab30f841f379d3d961f28c62f636e5596b30bf2199b43e198531cb66be7f2277", "fetched_at": "2026-07-12T02:40:15.407Z", "recordings": [ { "recording_id": "2cc9212882c3e9863c057bb1f115ba7dd84428821f00d9f032ab36ddab743fc3", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3db/3db884f681b7c8eeacd54c15106db8128dfad63c1c24e1702eadcf727be76bb2.mp3", "archive_relative_path": "raw/audio/3db/3db884f681b7c8eeacd54c15106db8128dfad63c1c24e1702eadcf727be76bb2.mp3" } ] } ], "prediction": "Pugwelga'latl ugta'sitl.", "reference": "We'gwijaqalta'tl atnaqanigtug." }, { "id": "mic-sent-46c0803dd33dd8f1b4b5dcab:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's getting cold again.", "output_text": "Gi's ap pemitge'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's getting cold again.", "mic_Latn": "Gi's ap pemitge'g." }, "canonical_ref": "entries/p/pemitge'g/pemitge'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-eaa5b4149e936b4e7572", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemitge'g/pemitge'g.html", "entry_url": "https://mikmaqonline.org/entries/p/pemitge'g/pemitge'g.html", "headword": "pemitge'g", "example_index": 0, "raw_html_path": "raw/entries/232244f13592bf666fd15a7d3ebf85d07d85bc70ca9c52b5fa82924bc390b7cd.html", "raw_html_sha256": "58077faaeec0317b9c3b4237b081b7dc4c577a2a275fe166a86350a7dd06842e", "fetched_at": "2026-07-12T02:43:33.710Z", "recordings": [ { "recording_id": "2b4bc9ebef92c6e0d1b81d7357743cf71d5ff135897242fda24098322ef559fb", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7f2/7f283317dd4e6f246c7242f604b10d077116ea22e25bb070fdcb5ef545de2116.mp3", "archive_relative_path": "raw/audio/7f2/7f283317dd4e6f246c7242f604b10d077116ea22e25bb070fdcb5ef545de2116.mp3" } ] } ], "prediction": "Gi's newte'g.", "reference": "Gi's ap pemitge'g." }, { "id": "mic-sent-46f603ee28121e9cb8b1bdce:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she says that he/she wants to take every basket he/she makes down river.", "output_text": "Teluet getu' papga'toq ta'n te's'g ligpenigan gisitoq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she says that he/she wants to take every basket he/she makes down river.", "mic_Latn": "Teluet getu' papga'toq ta'n te's'g ligpenigan gisitoq." }, "canonical_ref": "entries/p/papga'toq/papga'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a7637d5708d959113162", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/papga'toq/papga'toq.html", "entry_url": "https://mikmaqonline.org/entries/p/papga'toq/papga'toq.html", "headword": "papga'toq", "example_index": 0, "raw_html_path": "raw/entries/97e3f55eb1f422aa01117bf65cf6909e15b4828db76942e43fc3cc057439ad7b.html", "raw_html_sha256": "131d438a03bda814aa0ef87110e09fc986a7910dede3c693dba23523ff0eaf88", "fetched_at": "2026-07-12T02:43:08.385Z", "recordings": [ { "recording_id": "ae6c783ccc53b14c2004c15fd3a1400a2bc0640c38bc6fa9131e688764c6fc42", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e5d/e5dd3581e96351fc945a850fbd28baadf7a2d50fcc877140663827fdcbb30b7e.mp3", "archive_relative_path": "raw/audio/e5d/e5dd3581e96351fc945a850fbd28baadf7a2d50fcc877140663827fdcbb30b7e.mp3" } ] } ], "prediction": "Telta'latl te's'g ta'n te'sipo'q te'sigwa'toq.", "reference": "Teluet getu' papga'toq ta'n te's'g ligpenigan gisitoq." }, { "id": "mic-sent-4740872435ea224206d25f65:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend here owes a lot everywhere.", "output_text": "Ula nitap ma'munitettuet ms't tami.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend here owes a lot everywhere.", "mic_Latn": "Ula nitap ma'munitettuet ms't tami." }, "canonical_ref": "entries/t/tettuet/tettuet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-280e3b142c9700228478", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tettuet/tettuet.html", "entry_url": "https://mikmaqonline.org/entries/t/tettuet/tettuet.html", "headword": "tettuet", "example_index": 0, "raw_html_path": "raw/entries/1076a190ae4a16ba1ac4eefb2ffd024a82821690c9620c6646fb19298b0432d5.html", "raw_html_sha256": "fbea19292de61ded99be8ab1e8938936a199f7f2625748f6f7c978cc825ede0c", "fetched_at": "2026-07-12T02:45:51.284Z", "recordings": [ { "recording_id": "6e7b80dfafe148f1a7884951cb6fe3ce352207a55b4c2f301ed5f6318f8bd9be", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/460/460e4884fc10beb4a6ea1ba870beb2b0708c5b20b3b9938ce95e46290a9e934c.mp3", "archive_relative_path": "raw/audio/460/460e4884fc10beb4a6ea1ba870beb2b0708c5b20b3b9938ce95e46290a9e934c.mp3" } ] } ], "prediction": "Ula nitap ula mesgi'g na te's'g ta'n te'siw.", "reference": "Ula nitap ma'munitettuet ms't tami." }, { "id": "mic-sent-4788deebbde4ff6ef14ea6ba:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Be careful, I have already burnt myself there.", "output_text": "Ango'te'n, gi 's ni'n etlgaqsi.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Be careful, I have already burnt myself there.", "mic_Latn": "Ango'te'n, gi 's ni'n etlgaqsi." }, "canonical_ref": "entries/g/gaqsit/gaqsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-947848abded05278b4d6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gaqsit/gaqsit.html", "entry_url": "https://mikmaqonline.org/entries/g/gaqsit/gaqsit.html", "headword": "gaqsit", "example_index": 0, "raw_html_path": "raw/entries/c084cc402ae9c6b3e262bdcb9b398fc70574e976ac24f448b8bb348b8c338390.html", "raw_html_sha256": "f12223d011924dccafb00caf1d7742121971310d769ec6aaf67f3ca32f624f74", "fetched_at": "2026-07-12T02:38:42.404Z", "recordings": [ { "recording_id": "2fa26c39b01c3c590d3e8c09840d2dc97a254623e3dd0e97fe6b6ca2e7d0173e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/12d/12db2f5ac33ecaa9dc2ed781fcdf391465d1d6184953d2ead492c9ffee811b37.mp3", "archive_relative_path": "raw/audio/12d/12db2f5ac33ecaa9dc2ed781fcdf391465d1d6184953d2ead492c9ffee811b37.mp3" } ] } ], "prediction": "Ango'te'l, gi's gisga's'g na ula.", "reference": "Ango'te'n, gi 's ni'n etlgaqsi." }, { "id": "mic-sent-47cbf9fbed68d3e7e8b0e8cc:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What is the name of the female native chief that was just elected?", "output_text": "Taluisit na lnu saqama'sgw gisipisgwa't?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What is the name of the female native chief that was just elected?", "mic_Latn": "Taluisit na lnu saqama'sgw gisipisgwa't?" }, "canonical_ref": "entries/l/lnu_saqama'sgw/lnu_saqama'sgw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-744dde61af4c019b319a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lnu_saqama'sgw/lnu_saqama'sgw.html", "entry_url": "https://mikmaqonline.org/entries/l/lnu_saqama'sgw/lnu_saqama'sgw.html", "headword": "lnu_saqama'sgw", "example_index": 0, "raw_html_path": "raw/entries/3f962d1f6e82c0d97c460fee3dc563f98c1a5e3ea511b2941be2052743f3ad34.html", "raw_html_sha256": "facd821e692741c8858bbe6e42c0ae3638aebc5eecf913079e713b46cc676c22", "fetched_at": "2026-07-12T02:40:37.493Z", "recordings": [ { "recording_id": "056c5b7dec75094a7cb257d1c613ad6b52700f3850aa150837f661aaf3de0f5b", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fa7/fa7c5c83676103eaec99d8936eb442b26c6ccdae07086ec84e935cabb7ca1ac4.mp3", "archive_relative_path": "raw/audio/fa7/fa7c5c83676103eaec99d8936eb442b26c6ccdae07086ec84e935cabb7ca1ac4.mp3" } ] } ], "prediction": "Ta'n te's'g ta'n tujiw gisijig?", "reference": "Taluisit na lnu saqama'sgw gisipisgwa't?" }, { "id": "mic-sent-47f25fcc8b58fa6be3ec5e09:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I hear him/her talking, but I don't know what he/she is talking about.", "output_text": "Nutaq metewo'gwet, pas'g mu gejiaq ta'n goqwei wesgu'tg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I hear him/her talking, but I don't know what he/she is talking about.", "mic_Latn": "Nutaq metewo'gwet, pas'g mu gejiaq ta'n goqwei wesgu'tg." }, "canonical_ref": "entries/m/metewo'gwet/metewo'gwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d8aec89982af76784fc9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/metewo'gwet/metewo'gwet.html", "entry_url": "https://mikmaqonline.org/entries/m/metewo'gwet/metewo'gwet.html", "headword": "metewo'gwet", "example_index": 0, "raw_html_path": "raw/entries/a1759f7adda16acf4f129f683e709f79d591e83d4b052f131f9323b564281cda.html", "raw_html_sha256": "1ab57ecf72f05b42a25f5428b3b7e35c6ffabc497bf394aa5c5ad3596c406c38", "fetched_at": "2026-07-12T02:41:27.193Z", "recordings": [ { "recording_id": "52e4d0bf17840921433b8b88c6fbf30460449b17a09120d584c32ec8bbe62327", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e61/e6142c38563d26fbac65e7504ac9967d58d4b094000af9ddd9e6b12b2f9962c5.mp3", "archive_relative_path": "raw/audio/e61/e6142c38563d26fbac65e7504ac9967d58d4b094000af9ddd9e6b12b2f9962c5.mp3" } ] } ], "prediction": "Etlugowa'toq, gatu mu gejiaq ta'n goqwei.", "reference": "Nutaq metewo'gwet, pas'g mu gejiaq ta'n goqwei wesgu'tg." }, { "id": "mic-sent-48f5dfe803b4d43e544bc41a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The story teller is speaking about the past.", "output_text": "Wejgwa'tegemgeg a'tugwewinu wesgu'tg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The story teller is speaking about the past.", "mic_Latn": "Wejgwa'tegemgeg a'tugwewinu wesgu'tg." }, "canonical_ref": "entries/a/a'tugwewinu/a'tugwewinu.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bf910d8902ceb867bc30", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/a'tugwewinu/a'tugwewinu.html", "entry_url": "https://mikmaqonline.org/entries/a/a'tugwewinu/a'tugwewinu.html", "headword": "a'tugwewinu", "example_index": 0, "raw_html_path": "raw/entries/952637874d7e7accd7604bf812ed9d4221dde989acfa928d997950c63e46bdde.html", "raw_html_sha256": "09c02ee7c9ba76ec46f6d06c4866296cda9530cf6ad880cb7247cc559816e1ce", "fetched_at": "2026-07-12T02:37:27.557Z", "recordings": [ { "recording_id": "b84da19681efb926f63725073b6a7eb2a0cc973608e454f5bb5f5a259b5843b3", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d6e/d6e2924dfbb3ddbadcfc03adc46f82cfcd8d704b0c291084b193e3c255340ce4.mp3", "archive_relative_path": "raw/audio/d6e/d6e2924dfbb3ddbadcfc03adc46f82cfcd8d704b0c291084b193e3c255340ce4.mp3" } ] } ], "prediction": "Nuji'jig telta'latl gesgmnaq.", "reference": "Wejgwa'tegemgeg a'tugwewinu wesgu'tg." }, { "id": "mic-sent-490198f2e642cf4bbdeea5ec:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "First he/she cursed at him/her before throwing him/her out.", "output_text": "Jel tmg anmimatl gesgmnaq tewegegw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "First he/she cursed at him/her before throwing him/her out.", "mic_Latn": "Jel tmg anmimatl gesgmnaq tewegegw." }, "canonical_ref": "entries/a/almimatl/almimatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d2338b88d81a47559473", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/almimatl/almimatl.html", "entry_url": "https://mikmaqonline.org/entries/a/almimatl/almimatl.html", "headword": "almimatl", "example_index": 0, "raw_html_path": "raw/entries/6659a9b36ec4f2d668b2519ddb3a08fe1b1d96da6a89f4a45466dfc17c3f26bd.html", "raw_html_sha256": "4dd34ded5592dded8f521a9bc63b3e70f197c90c02a68062ed86dfee7a2d7e47", "fetched_at": "2026-07-12T02:36:41.827Z", "recordings": [ { "recording_id": "329d3039f33fc36a0b3a078045850788c5c3e86619935d4e0a72fb4680cb07f2", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fa5/fa53c2d16d8e6de7288b43bf0716d86448ffd44ea0972698319de2cda9082a44.mp3", "archive_relative_path": "raw/audio/fa5/fa53c2d16d8e6de7288b43bf0716d86448ffd44ea0972698319de2cda9082a44.mp3" } ] } ], "prediction": "Tami gesatg gesgmnaq mu'n tujiw gesgma'toq.", "reference": "Jel tmg anmimatl gesgmnaq tewegegw." }, { "id": "mic-sent-4903359b9926d3a060abbf9a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she grasps the cross and prays.", "output_text": "Sepitja'toq guljie'wei aq a'sutmat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she grasps the cross and prays.", "mic_Latn": "Sepitja'toq guljie'wei aq a'sutmat." }, "canonical_ref": "entries/s/sepitja'toq/sepitja'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-075e8fc9d1353cc77efa", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sepitja'toq/sepitja'toq.html", "entry_url": "https://mikmaqonline.org/entries/s/sepitja'toq/sepitja'toq.html", "headword": "sepitja'toq", "example_index": 0, "raw_html_path": "raw/entries/f157f1ee557de0ef309aa9396eb3f7ac2ff6b72cae8834e4cdcc2cf76716a2f2.html", "raw_html_sha256": "0b1f4e0f98d54cc629ada2b4fda71139b743038cacfc62c5d65273332a3ed11c", "fetched_at": "2026-07-12T02:44:49.487Z", "recordings": [ { "recording_id": "cdf274f0012b34075383bb6ae0eeb4e6ea3210eabc9e0972abe0531862d2f8e9", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/697/697f519aea2e92ef9ed64f67f86ce473a4061b5dc1f80f60aa642bfcaa8ae002.mp3", "archive_relative_path": "raw/audio/697/697f519aea2e92ef9ed64f67f86ce473a4061b5dc1f80f60aa642bfcaa8ae002.mp3" } ] } ], "prediction": "E'watl gesgm'g aq mesga'latl.", "reference": "Sepitja'toq guljie'wei aq a'sutmat." }, { "id": "mic-sent-4a32c5b2e19f4a3a7d03df55:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she knows how to sing, but he/she is very shy.", "output_text": "Natawintoq, pas'g gatu mawintage'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she knows how to sing, but he/she is very shy.", "mic_Latn": "Natawintoq, pas'g gatu mawintage'g." }, "canonical_ref": "entries/n/natawintoq/natawintoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-05f358008bf9d96684ba", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/natawintoq/natawintoq.html", "entry_url": "https://mikmaqonline.org/entries/n/natawintoq/natawintoq.html", "headword": "natawintoq", "example_index": 0, "raw_html_path": "raw/entries/59da01c0ca8fe0e28cb248489affd2c882cc7daef3650bb0a5c48ab49976947c.html", "raw_html_sha256": "0e798254c24f975698d0f82b87376668158a38707067324b58cc213490e39adc", "fetched_at": "2026-07-12T02:42:11.981Z", "recordings": [ { "recording_id": "d52208590701dee69ce7ce66952b711bc0f894b4991e4b8e93410879687b4396", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/029/0299def5db78420b9d17f96baefb2652c7b2a19259aaba5ccec30d5453fb7ac5.mp3", "archive_relative_path": "raw/audio/029/0299def5db78420b9d17f96baefb2652c7b2a19259aaba5ccec30d5453fb7ac5.mp3" } ] } ], "prediction": "We'gwi'g ta'n tujiw, gatu gi's na'te'g.", "reference": "Natawintoq, pas'g gatu mawintage'g." }, { "id": "mic-sent-4ad34bb403e32d7449eb9fb7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she sends his/her friend to where it is dangerous.", "output_text": "Pitgimatl witapal ta'n etlinsanoqonig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she sends his/her friend to where it is dangerous.", "mic_Latn": "Pitgimatl witapal ta'n etlinsanoqonig." }, "canonical_ref": "entries/p/pitgimatl/pitgimatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-99e688c52011eafe4581", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pitgimatl/pitgimatl.html", "entry_url": "https://mikmaqonline.org/entries/p/pitgimatl/pitgimatl.html", "headword": "pitgimatl", "example_index": 0, "raw_html_path": "raw/entries/63b9bce0fe31000f3d9de3427d43711ca5b156ff306cdc71301a67370bec5668.html", "raw_html_sha256": "5b1fd3335ecb664996c95831b58eab470229f6c17fd9d4cfe86583dcc1d8fbe2", "fetched_at": "2026-07-12T02:44:07.601Z", "recordings": [ { "recording_id": "e2c99c24e259d60bfd57dd3e0943e9f186dc18cfb6d067206d66172d5aaa0f64", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9be/9be33a862ebfd78aec6d4903e3c10e971df07c4a3c941d8591fef2a662c123ea.mp3", "archive_relative_path": "raw/audio/9be/9be33a862ebfd78aec6d4903e3c10e971df07c4a3c941d8591fef2a662c123ea.mp3" } ] } ], "prediction": "Amujpa'latl witapal ta'n tujiw negm.", "reference": "Pitgimatl witapal ta'n etlinsanoqonig." }, { "id": "mic-sent-4ae0048f366faf3feebaba4f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Are you running in the coming election?", "output_text": "Ula wejgu'aq ninasu'nm'gewei elegen?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Are you running in the coming election?", "mic_Latn": "Ula wejgu'aq ninasu'nm'gewei elegen?" }, "canonical_ref": "entries/n/ninasu'nm'gewei/ninasu'nm'gewei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f8434e5d64986ce3ae74", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ninasu'nm'gewei/ninasu'nm'gewei.html", "entry_url": "https://mikmaqonline.org/entries/n/ninasu'nm'gewei/ninasu'nm'gewei.html", "headword": "ninasu'nm'gewei", "example_index": 0, "raw_html_path": "raw/entries/e967637b056dd46b4735551e636bdd58d91a5a7b87222ee2e1c10a26d29f7e6a.html", "raw_html_sha256": "5392a0bc8b088d35dae196d52d4c94bbdbcddb93f72222645bdb4e989aa598cd", "fetched_at": "2026-07-12T02:42:34.119Z", "recordings": [ { "recording_id": "be5acdc8e4a762a95b9a5d457e5c8d922ab15a1b3ac00f01d9d333c9399b2f08", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d11/d111304079a98bb95ed8f831e09a4796eedd702fa28355702de63210eda3df0e.mp3", "archive_relative_path": "raw/audio/d11/d111304079a98bb95ed8f831e09a4796eedd702fa28355702de63210eda3df0e.mp3" } ] } ], "prediction": "Gi's gi's na we'gwigtug?", "reference": "Ula wejgu'aq ninasu'nm'gewei elegen?" }, { "id": "mic-sent-4af69b00a53592e1080b791d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has only one dollar left.", "output_text": "Pas'g newtaig piamiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has only one dollar left.", "mic_Latn": "Pas'g newtaig piamiet." }, "canonical_ref": "entries/p/piamiet/piamiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8ee112610cf5e8846d27", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/piamiet/piamiet.html", "entry_url": "https://mikmaqonline.org/entries/p/piamiet/piamiet.html", "headword": "piamiet", "example_index": 0, "raw_html_path": "raw/entries/a982ac60ceb0f5668da6fb713db1a7a63b0968e5c3faa2c5bd34cb11a7e71194.html", "raw_html_sha256": "b804460422c877b293d4fb668743d3fe18768b2e176acc31a763dc2d008ee6b9", "fetched_at": "2026-07-12T02:43:52.709Z", "recordings": [ { "recording_id": "18ea01b49aad42b61d72a9a7805186cd102166b001ce527a0a6e51fe0c009bde", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bae/bae8ac93c042619b3b7d3c2f8606e51657c3ce8d46502a19b80a880d8941658c.mp3", "archive_relative_path": "raw/audio/bae/bae8ac93c042619b3b7d3c2f8606e51657c3ce8d46502a19b80a880d8941658c.mp3" } ] } ], "prediction": "Pas'g pas'g newte'l gaqapi'l.", "reference": "Pas'g newtaig piamiet." }, { "id": "mic-sent-4b029888a019654d09de33ec:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little girl often tells on her older brother.", "output_text": "E'pite'ji'j gaqi'sg mesimatl ugsisl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little girl often tells on her older brother.", "mic_Latn": "E'pite'ji'j gaqi'sg mesimatl ugsisl." }, "canonical_ref": "entries/m/mesimatl/mesimatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bf9fbe4cb45e366f6c85", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mesimatl/mesimatl.html", "entry_url": "https://mikmaqonline.org/entries/m/mesimatl/mesimatl.html", "headword": "mesimatl", "example_index": 0, "raw_html_path": "raw/entries/a60e88f39bf79f802cc87afeb352e928602403bb5f09c8d01ed787aa908a7a71.html", "raw_html_sha256": "4626f7f785fe04e1576bb0f12c31a02882c35da55ae1d40ef59c897a4b8db5f6", "fetched_at": "2026-07-12T02:41:21.515Z", "recordings": [ { "recording_id": "1c4b03433c1167efc4c882b6a0d4e8ca7e72efabf77d66d771a78e1b52f67342", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ed1/ed13fd59e32a2d542e75eccace73855d6162270546a9a657f62e629fd5729703.mp3", "archive_relative_path": "raw/audio/ed1/ed13fd59e32a2d542e75eccace73855d6162270546a9a657f62e629fd5729703.mp3" } ] } ], "prediction": "E'pite'ji'j gaqa'latl ugjignaml.", "reference": "E'pite'ji'j gaqi'sg mesimatl ugsisl." }, { "id": "mic-sent-4b12dbd6f00f8f908ece0e27:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is shivering, the cold must be getting through his/her clothing.", "output_text": "Etlnng'tesing, amuj na saptaqsing.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is shivering, the cold must be getting through his/her clothing.", "mic_Latn": "Etlnng'tesing, amuj na saptaqsing." }, "canonical_ref": "entries/s/saptaqsing/saptaqsing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8ddf7f29de1cdfd33076", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/saptaqsing/saptaqsing.html", "entry_url": "https://mikmaqonline.org/entries/s/saptaqsing/saptaqsing.html", "headword": "saptaqsing", "example_index": 0, "raw_html_path": "raw/entries/851bc573663b6dad6b05e5ea2526bbbd6b1025018bc0e1d6b90fb739b791ae2d.html", "raw_html_sha256": "92cdbe127a5a0423719f02e0976d698a3bd97d8e6ba10ae6fd348d822d58fb2e", "fetched_at": "2026-07-12T02:36:07.340Z", "recordings": [ { "recording_id": "5e3a2594c60e74017d1e6d0e978016d28c6099433c37f3d1ca0a56ac6d459c4c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/422/4221b9c626c9a0b73d9352f5779ea271f7e3c5ce329d719255a121bec738721b.mp3", "archive_relative_path": "raw/audio/422/4221b9c626c9a0b73d9352f5779ea271f7e3c5ce329d719255a121bec738721b.mp3" } ] } ], "prediction": "Pugwelg, amujpa gmu'j gesatg ugjit.", "reference": "Etlnng'tesing, amuj na saptaqsing." }, { "id": "mic-sent-4b2882f55d0ec05ac07906ab:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My dog has only one eye.", "output_text": "Ula nti pas'g newtaqigwat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My dog has only one eye.", "mic_Latn": "Ula nti pas'g newtaqigwat." }, "canonical_ref": "entries/n/newtalqigwat/newtalqigwat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4c957a42afc76031d92d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/newtalqigwat/newtalqigwat.html", "entry_url": "https://mikmaqonline.org/entries/n/newtalqigwat/newtalqigwat.html", "headword": "newtalqigwat", "example_index": 0, "raw_html_path": "raw/entries/9df3890b1f752746943252da709f33f4ce891962fcfbfe5517f67144483bf0b5.html", "raw_html_sha256": "62d9b16f0b7f7f0bbb0e9e7182c227d8a410c7a119f6b51883e04e624f008120", "fetched_at": "2026-07-12T02:42:27.672Z", "recordings": [ { "recording_id": "91737189ccbe3147b0ab757ee210bb34b4cb272126fc983c70c9b12ca4b9df81", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d8c/d8c640e360f032a82a5af8f50ac96b032fadee42cce1747898fcce678f1292bf.mp3", "archive_relative_path": "raw/audio/d8c/d8c640e360f032a82a5af8f50ac96b032fadee42cce1747898fcce678f1292bf.mp3" } ] } ], "prediction": "Nmu'ji'j pas'g newte'g elie'g.", "reference": "Ula nti pas'g newtaqigwat." }, { "id": "mic-sent-4bd993193038c205b47ab18d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary Ann is aiming for higher education.", "output_text": "Malia'n nattesg'g espe'teg gina'masuti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary Ann is aiming for higher education.", "mic_Latn": "Malia'n nattesg'g espe'teg gina'masuti." }, "canonical_ref": "entries/n/nattesg'g/nattesg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bb57f3b9032c27ccfc9e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nattesg'g/nattesg'g.html", "entry_url": "https://mikmaqonline.org/entries/n/nattesg'g/nattesg'g.html", "headword": "nattesg'g", "example_index": 0, "raw_html_path": "raw/entries/7d0814119846858a1e200088583d4713c427dff5c40775bb7aecd2c12ad02cf9.html", "raw_html_sha256": "ff0d1243dfffe09fb35f78f0f5378eeda83facfe48a5da9a8f1b32456791b216", "fetched_at": "2026-07-12T02:42:14.013Z", "recordings": [ { "recording_id": "04705c428dd2f06b4ee90140b9d9e66b3a740a3ff5a96ecc9e6c52ec9a3004e2", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ed9/ed9b83e51967e4f8e782f199a36af1d32ef075116d0ab8ec8c6b1c848497f8bc.mp3", "archive_relative_path": "raw/audio/ed9/ed9b83e51967e4f8e782f199a36af1d32ef075116d0ab8ec8c6b1c848497f8bc.mp3" } ] } ], "prediction": "Malia'n gesatg ugjit.", "reference": "Malia'n nattesg'g espe'teg gina'masuti." }, { "id": "mic-sent-4bfd38abd6229c22725c6420:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My brother Joseph is an illusionist.", "output_text": "Njignam So'sep na milaplgigwa'teget.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My brother Joseph is an illusionist.", "mic_Latn": "Njignam So'sep na milaplgigwa'teget." }, "canonical_ref": "entries/m/milaplgigwa'teget/milaplgigwa'teget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4cdacc100808b154eb95", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/milaplgigwa'teget/milaplgigwa'teget.html", "entry_url": "https://mikmaqonline.org/entries/m/milaplgigwa'teget/milaplgigwa'teget.html", "headword": "milaplgigwa'teget", "example_index": 0, "raw_html_path": "raw/entries/6e4c7e6eb806267b4e40387a62557714e4a9d36c9313f8ecdbb67b3899228645.html", "raw_html_sha256": "a7fb15354eb57da0bd96e1d687300c5c339c3a51fee3f529d97b91bfd117ed3b", "fetched_at": "2026-07-12T02:41:35.441Z", "recordings": [ { "recording_id": "10bce3a83c01924f023dc0aa7c686ffe948720003be1c17fa7c5f430c96028c5", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bc0/bc0a1507a9c95d90151873ae30eb22b3403bd02cf743b01a86e5d973b73999c8.mp3", "archive_relative_path": "raw/audio/bc0/bc0a1507a9c95d90151873ae30eb22b3403bd02cf743b01a86e5d973b73999c8.mp3" } ] } ], "prediction": "Nugu' So'sep na lugowaqanigtug.", "reference": "Njignam So'sep na milaplgigwa'teget." }, { "id": "mic-sent-4c0cf486ec4f4e6de86f8b1d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Why is this water slimy?", "output_text": "Talgis sisqalpo'qiaq ula samqwan?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Why is this water slimy?", "mic_Latn": "Talgis sisqalpo'qiaq ula samqwan?" }, "canonical_ref": "entries/s/sisqalpo'qiaq/sisqalpo'qiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f800d212b07d23080a1b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sisqalpo'qiaq/sisqalpo'qiaq.html", "entry_url": "https://mikmaqonline.org/entries/s/sisqalpo'qiaq/sisqalpo'qiaq.html", "headword": "sisqalpo'qiaq", "example_index": 0, "raw_html_path": "raw/entries/c8b313fd45a983b1fb751842da465e76668a684e28e06449d1a42ac48ad56d36.html", "raw_html_sha256": "0d8f23781210660e42bc165401211a75b4ca8d6207ecf0e505197447255e805c", "fetched_at": "2026-07-12T02:45:09.082Z", "recordings": [ { "recording_id": "896827c1d62b881524ba264ed75fa4dc5ec978c4d0d88ab308889f462dbb40e0", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/196/19630b06df55013f722503e7a184291815f729a5ca953b6b6f8d118f1c5d5116.mp3", "archive_relative_path": "raw/audio/196/19630b06df55013f722503e7a184291815f729a5ca953b6b6f8d118f1c5d5116.mp3" } ] } ], "prediction": "Goqwei na ula gmu'j?", "reference": "Talgis sisqalpo'qiaq ula samqwan?" }, { "id": "mic-sent-4c3646eb9d271f0d7e96a683:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she can break a board in two with his/her hands.", "output_text": "Negm na gistma'latl lasqo'plawl ugpignigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she can break a board in two with his/her hands.", "mic_Latn": "Negm na gistma'latl lasqo'plawl ugpignigtug." }, "canonical_ref": "entries/t/tema'latl/tema'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-208c99dd310b647b2ba4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tema'latl/tema'latl.html", "entry_url": "https://mikmaqonline.org/entries/t/tema'latl/tema'latl.html", "headword": "tema'latl", "example_index": 0, "raw_html_path": "raw/entries/86b0aec3ff80e1aec15f8299901a2781012ddb5091badbd791947ed1d56a1b5d.html", "raw_html_sha256": "283d3a2dd5170dea27a25f6d9448838f62ab207537a8b145665b1bfefbc14488", "fetched_at": "2026-07-12T02:45:36.218Z", "recordings": [ { "recording_id": "a1ae282124a7a4974d5997e20c4b832419489c7d77064597684b5782f31fc8c1", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/600/60008eb5127e2d8baebb43ce3ee1b5653f833a7a35248767af2559aff3425ec0.mp3", "archive_relative_path": "raw/audio/600/60008eb5127e2d8baebb43ce3ee1b5653f833a7a35248767af2559aff3425ec0.mp3" } ] } ], "prediction": "Amujpa'latl ugtaqanigtug.", "reference": "Negm na gistma'latl lasqo'plawl ugpignigtug." }, { "id": "mic-sent-4cda36dd9638f4ca2c4f046b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Is the maple sap boiling yet?", "output_text": "Gi's wejaqamiaq snaweiapu?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Is the maple sap boiling yet?", "mic_Latn": "Gi's wejaqamiaq snaweiapu?" }, "canonical_ref": "entries/w/wejaqamiaq/wejaqamiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ba7f0a715f0f416d3359", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejaqamiaq/wejaqamiaq.html", "entry_url": "https://mikmaqonline.org/entries/w/wejaqamiaq/wejaqamiaq.html", "headword": "wejaqamiaq", "example_index": 0, "raw_html_path": "raw/entries/88b994afdfabf315cf57084616fd0c36378d4c103e7a23d4cfff81f37935bf9f.html", "raw_html_sha256": "4bb2a0f0be9ed70c7ccfbd83725ff56e9ad3ad58a602b711c5f6e77d07478f1a", "fetched_at": "2026-07-12T02:46:48.277Z", "recordings": [ { "recording_id": "1d3de0e433129cbd5448568d4e437f754ae065669245727aa54a4b4374728797", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/510/5104685cfba89e69ef0730f52d4aca96e6dee3a19734613904f16b19b93f3717.mp3", "archive_relative_path": "raw/audio/510/5104685cfba89e69ef0730f52d4aca96e6dee3a19734613904f16b19b93f3717.mp3" } ] } ], "prediction": "Gi's gi's gmu'ji'j?", "reference": "Gi's wejaqamiaq snaweiapu?" }, { "id": "mic-sent-4d6e06d6d883a2222647ff32:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It goes by every day at five.", "output_text": "Te'sigisg'g na'n ajiet pemiaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It goes by every day at five.", "mic_Latn": "Te'sigisg'g na'n ajiet pemiaq." }, "canonical_ref": "entries/p/pemiaq/pemiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ac10e4bd80d8eeb65f8c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemiaq/pemiaq.html", "entry_url": "https://mikmaqonline.org/entries/p/pemiaq/pemiaq.html", "headword": "pemiaq", "example_index": 0, "raw_html_path": "raw/entries/c3a5b3ce5412113756f407eb8e7097e512d3b2035929344845db437be070a9ed.html", "raw_html_sha256": "507e406729f2b6b70b4794c6a7c60b79157237367270b98b7028730b8d87bace", "fetched_at": "2026-07-12T02:43:31.405Z", "recordings": [ { "recording_id": "83bd158c618effdce827874aaeb4795a0cdfad7a35f3d8563aae946cba0240a2", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6c9/6c92810b16c13749d398df2cf4d6cb9ff3b0848b2f5c774e54707157d4515ba3.mp3", "archive_relative_path": "raw/audio/6c9/6c92810b16c13749d398df2cf4d6cb9ff3b0848b2f5c774e54707157d4515ba3.mp3" } ] } ], "prediction": "Te'sipu'g te'sipow pilei.", "reference": "Te'sigisg'g na'n ajiet pemiaq." }, { "id": "mic-sent-4f0e2dff3d073f45c237f414:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "His/her house is old, but it continues to be a good house.", "output_text": "Saqawei wi'g gatu me' newte' teliamiuligana'q.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "His/her house is old, but it continues to be a good house.", "mic_Latn": "Saqawei wi'g gatu me' newte' teliamiuligana'q." }, "canonical_ref": "entries/a/amiuligana'q/amiuligana'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b4ff65e0e94b98a570fd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amiuligana'q/amiuligana'q.html", "entry_url": "https://mikmaqonline.org/entries/a/amiuligana'q/amiuligana'q.html", "headword": "amiuligana'q", "example_index": 0, "raw_html_path": "raw/entries/0e19dc0605e430d19801b4e2f01887cb729589c453fb1e97ae72e1fc3ad2746f.html", "raw_html_sha256": "8289fa77cddf42fd98249ff259978113f79526f321d4864008239d268aa8e3ac", "fetched_at": "2026-07-12T02:36:02.768Z", "recordings": [ { "recording_id": "82e622accb7a220eeb67c6ef6fe93593461a7538009b8ec053fda67271e4cae7", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/927/927a428cde391980dab1cf5d6a919bccb74098b99b696cce439a6e4502e6a435.mp3", "archive_relative_path": "raw/audio/927/927a428cde391980dab1cf5d6a919bccb74098b99b696cce439a6e4502e6a435.mp3" } ] } ], "prediction": "We'gwi'g ugjit, gatu gisijig we'gwigsit.", "reference": "Saqawei wi'g gatu me' newte' teliamiuligana'q." }, { "id": "mic-sent-4faf9527670bed63b3dcc6fb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There is a leak somewhere because the floor is wet.", "output_text": "Na'tami espeg muta msaqtaqt saqpe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There is a leak somewhere because the floor is wet.", "mic_Latn": "Na'tami espeg muta msaqtaqt saqpe'g." }, "canonical_ref": "entries/e/espeg/espeg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-70b86655256037016699", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/espeg/espeg.html", "entry_url": "https://mikmaqonline.org/entries/e/espeg/espeg.html", "headword": "espeg", "example_index": 0, "raw_html_path": "raw/entries/b60f0a27901bc0faa70110674e24f3e1ebb2eafa77857cad9201fe4b8bb715e4.html", "raw_html_sha256": "6c986c5d87f55489277bf87887978b28c75311f8c7120162cc0ee2e6bbb855c4", "fetched_at": "2026-07-12T02:38:18.974Z", "recordings": [ { "recording_id": "1a9e5cab73fe150149b3d01edf15acf37f73aca4664be14323f69c11772d25a9", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b1a/b1af08640103929f6148abca7b8cfcdd1197316d3710ed2af6b697bf9219fcd8.mp3", "archive_relative_path": "raw/audio/b1a/b1af08640103929f6148abca7b8cfcdd1197316d3710ed2af6b697bf9219fcd8.mp3" } ] } ], "prediction": "Lpa we'gwi'g ta'n muta lugowaqan.", "reference": "Na'tami espeg muta msaqtaqt saqpe'g." }, { "id": "mic-sent-4fd150981885311708ff4849:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend just came from town and is fussing about what is happening there.", "output_text": "Nitap wejiet qame'g aq sesputg ta'n teliaq na'te'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend just came from town and is fussing about what is happening there.", "mic_Latn": "Nitap wejiet qame'g aq sesputg ta'n teliaq na'te'l." }, "canonical_ref": "entries/s/sesputg/sesputg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-78672bdf68bf6ec811e8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sesputg/sesputg.html", "entry_url": "https://mikmaqonline.org/entries/s/sesputg/sesputg.html", "headword": "sesputg", "example_index": 0, "raw_html_path": "raw/entries/32f865fb512ac76e1023e5bbc8f5f4bdbe7ff105cf8bcd954d8eed8cd1827896.html", "raw_html_sha256": "2a268937a2244ac53ac9306fcb63765899dbb13014fcc718b2176eda54eeda1c", "fetched_at": "2026-07-12T02:44:54.124Z", "recordings": [ { "recording_id": "4cbc5a9fbf890670621562bc1e1c95f9a0a74a10a9d8166c3b0d37b507812395", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/094/094ee9a19bc312e0c04ce3a2da2744463b03a5e4d2c19c0511321b78af9f8e24.mp3", "archive_relative_path": "raw/audio/094/094ee9a19bc312e0c04ce3a2da2744463b03a5e4d2c19c0511321b78af9f8e24.mp3" } ] } ], "prediction": "Nitap newte'gwit aq te's'g ta'n goqwei etlugsugwet.", "reference": "Nitap wejiet qame'g aq sesputg ta'n teliaq na'te'l." }, { "id": "mic-sent-4ff22b36afff62aa68dede59:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Watch that horse jump.", "output_text": "Ge' angam wenaqiet na te'sipow.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Watch that horse jump.", "mic_Latn": "Ge' angam wenaqiet na te'sipow." }, "canonical_ref": "entries/w/wenaqiet/wenaqiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5f024f744bbdcb58cbd7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wenaqiet/wenaqiet.html", "entry_url": "https://mikmaqonline.org/entries/w/wenaqiet/wenaqiet.html", "headword": "wenaqiet", "example_index": 0, "raw_html_path": "raw/entries/2f8f900a8aecf863938f2b0d678a85ea23298c4fb49a581a66d889d3d88cd8dc.html", "raw_html_sha256": "5529389f5154aca025d366243efa047a74a8a7d806dd345b2d5ee64321b36e22", "fetched_at": "2026-07-12T02:47:11.716Z", "recordings": [ { "recording_id": "a85900fea492d97492538c878f75afe5bd8b4383f799bdb15181dba2cdccba88", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c6b/c6b5bce87327a619e30fc7aa4f67e1627fcafd315d467d91f6661e80f7667f6b.mp3", "archive_relative_path": "raw/audio/c6b/c6b5bce87327a619e30fc7aa4f67e1627fcafd315d467d91f6661e80f7667f6b.mp3" } ] } ], "prediction": "Ango'te'l na te'sipow glapis.", "reference": "Ge' angam wenaqiet na te'sipow." }, { "id": "mic-sent-500ddd28988c2bf047739bb7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You should see his/her face, he/she must have been naping on it.", "output_text": "Nmituaq ugsisgw, npa'ji'jitug tetuji(w) mawmunielg'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You should see his/her face, he/she must have been naping on it.", "mic_Latn": "Nmituaq ugsisgw, npa'ji'jitug tetuji(w) mawmunielg'g." }, "canonical_ref": "entries/e/elg'g/elg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bf6eb0da16590996ce8b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elg'g/elg'g.html", "entry_url": "https://mikmaqonline.org/entries/e/elg'g/elg'g.html", "headword": "elg'g", "example_index": 0, "raw_html_path": "raw/entries/351f1a4b2cca4aa0661bdadfb6a8917216b937a38a804cd29fa0e9754e8a5bca.html", "raw_html_sha256": "951c4913e6ff2f11a115982cf4a3042a18758f286df5ab320e78785f3b7ab68b", "fetched_at": "2026-07-12T02:37:43.240Z", "recordings": [ { "recording_id": "93ccc46badafe811200edbcea4909411af5f048250631a760410852e1d299e9a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e8f/e8fe7d14a93bb1d1bad93bb5f60207f701c1f0becaba49d6e6b78ecae4a96eca.mp3", "archive_relative_path": "raw/audio/e8f/e8fe7d14a93bb1d1bad93bb5f60207f701c1f0becaba49d6e6b78ecae4a96eca.mp3" } ] } ], "prediction": "Amujpa'latl ugjitl, amujpa etlmisga'toq.", "reference": "Nmituaq ugsisgw, npa'ji'jitug tetuji(w) mawmunielg'g." }, { "id": "mic-sent-50987ecadf3546f2b93bee20:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "She unties the arpon.", "output_text": "Apgwa'toq laqpisuti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "She unties the arpon.", "mic_Latn": "Apgwa'toq laqpisuti." }, "canonical_ref": "entries/a/apgwa'toq/apgwa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-984e97344e92af8668a1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/apgwa'toq/apgwa'toq.html", "entry_url": "https://mikmaqonline.org/entries/a/apgwa'toq/apgwa'toq.html", "headword": "apgwa'toq", "example_index": 0, "raw_html_path": "raw/entries/ba374c826af5b0e109ba68ce20412f34a0176f46ea8c8011ec1de63b47496bd8.html", "raw_html_sha256": "f2e46bcc65aff0ddae3dcc03c90af8d73f130e7be69b61549cce3fbd039dbc97", "fetched_at": "2026-07-12T02:37:05.103Z", "recordings": [ { "recording_id": "c97fb1fdbd33d576f64bf403ad711423404627c7d85a61f279cc5fe6f4e77e06", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4ff/4ffe77ea51e7ad76088beee9b248dc12020ef42f77b263e32ae4f007434f838a.mp3", "archive_relative_path": "raw/audio/4ff/4ffe77ea51e7ad76088beee9b248dc12020ef42f77b263e32ae4f007434f838a.mp3" } ] } ], "prediction": "Gesatg na arpon.", "reference": "Apgwa'toq laqpisuti." }, { "id": "mic-sent-50b8cca6bb5bad3d1a9b9b42:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There must be someone who steals.", "output_text": "Miamuj eig natuen ta'n gemutnet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There must be someone who steals.", "mic_Latn": "Miamuj eig natuen ta'n gemutnet." }, "canonical_ref": "entries/g/gemutnet/gemutnet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e3b9361022b9d2c5a68c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gemutnet/gemutnet.html", "entry_url": "https://mikmaqonline.org/entries/g/gemutnet/gemutnet.html", "headword": "gemutnet", "example_index": 0, "raw_html_path": "raw/entries/0d0c9550959c658d2185dca0a46e28b2e3ed6f6cfda7ede3de66a848d57324e2.html", "raw_html_sha256": "525ec7076d76fda8ceb20822a51dfb81d6ee5f3d1b198be0e85191e1ae1cc2db", "fetched_at": "2026-07-12T02:38:58.187Z", "recordings": [ { "recording_id": "78c892b3795d88077df259a12364766be726c9fe087db26fea2a7cb72a9becef", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a6f/a6f3df71e93dc26dc71e9870fdcdc05200f5194cd9a7a7b5abaf19071dff9811.mp3", "archive_relative_path": "raw/audio/a6f/a6f3df71e93dc26dc71e9870fdcdc05200f5194cd9a7a7b5abaf19071dff9811.mp3" } ] } ], "prediction": "Amujpa ni'n goqwei etlugowa'toq.", "reference": "Miamuj eig natuen ta'n gemutnet." }, { "id": "mic-sent-50f8b1f58c8d97f0179dd529:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There is a burning sensation where I injured my knee.", "output_text": "Wi'segesit na njigun ta'n jileiaqap.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There is a burning sensation where I injured my knee.", "mic_Latn": "Wi'segesit na njigun ta'n jileiaqap." }, "canonical_ref": "entries/w/wi'segesit/wi'segesit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c64f0c176ae1df164c9e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wi'segesit/wi'segesit.html", "entry_url": "https://mikmaqonline.org/entries/w/wi'segesit/wi'segesit.html", "headword": "wi'segesit", "example_index": 0, "raw_html_path": "raw/entries/3f9c9c851dbe655b54ce05a1ae6485438ab2fe91240b8da2c46946ad97e863a9.html", "raw_html_sha256": "4561c985b23f3bf5629de1f32303653387c879abda872c81d99a03fd043e2304", "fetched_at": "2026-07-12T02:47:38.163Z", "recordings": [ { "recording_id": "f43c383096f7ab01ed7b640e830954523013b2fc5a7f562781e57146a2c50737", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/961/961672c08624d7bdbd8f5e0020bc2e1b91c53de5c737ac95df29319caa8fb185.mp3", "archive_relative_path": "raw/audio/961/961672c08624d7bdbd8f5e0020bc2e1b91c53de5c737ac95df29319caa8fb185.mp3" } ] } ], "prediction": "Pugwelg ta'n tujiw gesatg.", "reference": "Wi'segesit na njigun ta'n jileiaqap." }, { "id": "mic-sent-51555bae9bfeab397b2fe4d7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I saw a full grown bull moose this morning.", "output_text": "Sepei nemi'g'p ge'tiap.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I saw a full grown bull moose this morning.", "mic_Latn": "Sepei nemi'g'p ge'tiap." }, "canonical_ref": "entries/g/ge'tiap/ge'tiap.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-46894a4f6d5b7137b4e8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/ge'tiap/ge'tiap.html", "entry_url": "https://mikmaqonline.org/entries/g/ge'tiap/ge'tiap.html", "headword": "ge'tiap", "example_index": 0, "raw_html_path": "raw/entries/2f7563191d3a2b8a925f8940f1bcbc9d83c82611efa68faae006921855511a4f.html", "raw_html_sha256": "62be71164f3778652f3893f9a521b8066068ba1c90b7e30ca4502da052f8478c", "fetched_at": "2026-07-12T02:39:22.592Z", "recordings": [ { "recording_id": "2d34d294da9a41cc44f106c037932729f35fec4a363beb1dc113329a6c4eef70", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dca/dcadad3b7af2e62224473e3f81cafc68b4fba622ae9b8a2e36a62c406fb44a93.mp3", "archive_relative_path": "raw/audio/dca/dcadad3b7af2e62224473e3f81cafc68b4fba622ae9b8a2e36a62c406fb44a93.mp3" } ] } ], "prediction": "Gi's'g ni'n nemi'g wi'gwi'g ula egsitpu'g.", "reference": "Sepei nemi'g'p ge'tiap." }, { "id": "mic-sent-516933f9a83ef9976b7c74fb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The cat is feeling around inside the hole for a mouse.", "output_text": "Gajue'wj nantunatl apigji'tl elmaqegigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The cat is feeling around inside the hole for a mouse.", "mic_Latn": "Gajue'wj nantunatl apigji'tl elmaqegigtug." }, "canonical_ref": "entries/n/nantunatl/nantunatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-efbc94d4738b28437c29", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nantunatl/nantunatl.html", "entry_url": "https://mikmaqonline.org/entries/n/nantunatl/nantunatl.html", "headword": "nantunatl", "example_index": 0, "raw_html_path": "raw/entries/24e9c3fb3c952401af90ec8e29276a119ab57cfc2100ca1733b1a985493443a6.html", "raw_html_sha256": "8de7a7d66c63c49204d7bba67ed34ee263efb87528e738bae576950c9dc98177", "fetched_at": "2026-07-12T02:41:59.993Z", "recordings": [ { "recording_id": "d46499c8a15e088c29c4b06ca143f27a6d19872eb36f1d49084063be7165c7d5", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/188/18834bb0bdb04f18e181fb24dfd6a47850e99214a1d68c8df3064dc49b0491d9.mp3", "archive_relative_path": "raw/audio/188/18834bb0bdb04f18e181fb24dfd6a47850e99214a1d68c8df3064dc49b0491d9.mp3" } ] } ], "prediction": "Gaju'ji'j etlmisga'latl ugtaqanigtug.", "reference": "Gajue'wj nantunatl apigji'tl elmaqegigtug." }, { "id": "mic-sent-5170062537eb8eb9e7d4f95c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Tie that rope.", "output_text": "Gltaqpil na a'papi.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Tie that rope.", "mic_Latn": "Gltaqpil na a'papi." }, "canonical_ref": "entries/a/a'papi/a'papi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-501831d956ba169775d1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/a'papi/a'papi.html", "entry_url": "https://mikmaqonline.org/entries/a/a'papi/a'papi.html", "headword": "a'papi", "example_index": 0, "raw_html_path": "raw/entries/c14e53d96ae6472f1cdeffaf58484481b8ecfc5850937226406b6ec5ddf16927.html", "raw_html_sha256": "31850d18f8b7327d948ac877acd2facfdc9beeb856f4172d4a1dfcb671067c78", "fetched_at": "2026-07-12T02:37:02.889Z", "recordings": [ { "recording_id": "8d73138a1103c42a635362bf8e1a7990a03ff44dcb892bf7b218e91071794365", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cf2/cf2cccfde734deed9d26f2e834832b05b052dc7500ec298fb6b6def412c1593d.mp3", "archive_relative_path": "raw/audio/cf2/cf2cccfde734deed9d26f2e834832b05b052dc7500ec298fb6b6def412c1593d.mp3" } ] } ], "prediction": "Ge's'g na lpa'toq.", "reference": "Gltaqpil na a'papi." }, { "id": "mic-sent-51e517ce9276f23e3e2f40e5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Two years John and I have been working night shift.", "output_text": "Gi's tapuipunqeg Sa'n niplugweieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Two years John and I have been working night shift.", "mic_Latn": "Gi's tapuipunqeg Sa'n niplugweieg." }, "canonical_ref": "entries/n/niplugwet/niplugwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bb0102a2e3b57ce19d5e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/niplugwet/niplugwet.html", "entry_url": "https://mikmaqonline.org/entries/n/niplugwet/niplugwet.html", "headword": "niplugwet", "example_index": 0, "raw_html_path": "raw/entries/20507929277bf2d68a2d756317d5cf95950d3fdce81e47a907c018666a6a2464.html", "raw_html_sha256": "9fda38eb53a7f8e878a3e0595d229ff4871f912394843a439218d50a4412fb1c", "fetched_at": "2026-07-12T02:36:24.847Z", "recordings": [ { "recording_id": "5f7981e14d21c6dc36a5ca03c40290b95be971ad04eb70e94535ab5c6a068299", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cb6/cb6189742c4f312949944c93b7c50aecdb656b4499dda7c046f471e87fe2b38c.mp3", "archive_relative_path": "raw/audio/cb6/cb6189742c4f312949944c93b7c50aecdb656b4499dda7c046f471e87fe2b38c.mp3" } ] } ], "prediction": "Te's'g gi's gi'l jugwa'tuatl ugjit.", "reference": "Gi's tapuipunqeg Sa'n niplugweieg." }, { "id": "mic-sent-52a495470bcbcaf715d841b0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The wind is out of the east.", "output_text": "Ugipenug wet'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The wind is out of the east.", "mic_Latn": "Ugipenug wet'g." }, "canonical_ref": "entries/u/ugjipen/ugjipen.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d3f30c9a6c33c0ab3ace", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugjipen/ugjipen.html", "entry_url": "https://mikmaqonline.org/entries/u/ugjipen/ugjipen.html", "headword": "ugjipen", "example_index": 0, "raw_html_path": "raw/entries/d3bce52470e929228b9c006d1327a9cff892712fea69a5117c86db4a3c4b09e7.html", "raw_html_sha256": "d26246f4ede06f40eacbff3430588a76cfca4819446655d3b8c9e361905d33ec", "fetched_at": "2026-07-12T02:46:11.612Z", "recordings": [ { "recording_id": "3acae90c519d53626da047421992c428d6de4822498b807f58280a4b8a5b64fe", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b87/b87b8ef58aa7bc07f5e77f46d3dbdce88910c968d5fc9fad7f8373d358ef325b.mp3", "archive_relative_path": "raw/audio/b87/b87b8ef58aa7bc07f5e77f46d3dbdce88910c968d5fc9fad7f8373d358ef325b.mp3" } ] } ], "prediction": "Pugwelg'g na gisigtug.", "reference": "Ugipenug wet'g." }, { "id": "mic-sent-536d4a3c6b559bedddae72a1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Carrots are very delicious.", "output_text": "Maw wigapugsijig na enmapejig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Carrots are very delicious.", "mic_Latn": "Maw wigapugsijig na enmapejig." }, "canonical_ref": "entries/e/enmapejit/enmapejit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-619feb8493983742939d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/enmapejit/enmapejit.html", "entry_url": "https://mikmaqonline.org/entries/e/enmapejit/enmapejit.html", "headword": "enmapejit", "example_index": 0, "raw_html_path": "raw/entries/1cc87ddecd126b2539b080d2f24a85fa8d1c38a876cbf6eade662719ce4c0d6c.html", "raw_html_sha256": "60cdfbac63bf082132e1820ceab5edd671248e1494b04a13a00eb061489cace7", "fetched_at": "2026-07-12T02:38:00.678Z", "recordings": [ { "recording_id": "bc7bde7b6c53f7c4e77271ab03ec75eee418c858b7e7d442b6f484c5c3950791", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c9e/c9e50147e43fe039b171154b1fcac28d544656a6f8304bf6cad16321b9b9ef2e.mp3", "archive_relative_path": "raw/audio/c9e/c9e50147e43fe039b171154b1fcac28d544656a6f8304bf6cad16321b9b9ef2e.mp3" } ] } ], "prediction": "Pugwelg na we'gwi'g.", "reference": "Maw wigapugsijig na enmapejig." }, { "id": "mic-sent-53986688013e3234c1c76727:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Bring the waltes plate and let's play.", "output_text": "Waltes jugwa'l aq laqatinej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Bring the waltes plate and let's play.", "mic_Latn": "Waltes jugwa'l aq laqatinej." }, "canonical_ref": "entries/w/waltes/waltes.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-80d0210dfb00ba06dcb2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waltes/waltes.html", "entry_url": "https://mikmaqonline.org/entries/w/waltes/waltes.html", "headword": "waltes", "example_index": 0, "raw_html_path": "raw/entries/05f927c249c323ad2a47424ada042aa118f1d9b372789f8b9ac930e65f42efca.html", "raw_html_sha256": "fb1d126acd87ab5af81e9dce71be88aff4cd6843bd22a6883fb12b71004bab5c", "fetched_at": "2026-07-12T02:46:30.900Z", "recordings": [ { "recording_id": "51f28ef7fd42a177c3fdab437c0840cf497028b636ab4cc1bd799b12cd6941a9", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/885/885ada9aa21718fb8796fa0e79f6b700cad3a6fb0146cbc32c6d2d64a44dfdd2.mp3", "archive_relative_path": "raw/audio/885/885ada9aa21718fb8796fa0e79f6b700cad3a6fb0146cbc32c6d2d64a44dfdd2.mp3" } ] } ], "prediction": "Amujpa wi'gwi'g na walte'l aq lugowa'sij.", "reference": "Waltes jugwa'l aq laqatinej." }, { "id": "mic-sent-543887f0284b2800f7ea3236:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where does the agent work?", "output_text": "Tami e'jnt etlugwet?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where does the agent work?", "mic_Latn": "Tami e'jnt etlugwet?" }, "canonical_ref": "entries/e/e'jnt/e'jnt.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bc86e4f15fd7f26e8723", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/e'jnt/e'jnt.html", "entry_url": "https://mikmaqonline.org/entries/e/e'jnt/e'jnt.html", "headword": "e'jnt", "example_index": 0, "raw_html_path": "raw/entries/ea6a6f233055235d3fde1290db0129df35a29352e1e500e037d7f9a44ad9e8c1.html", "raw_html_sha256": "715ec66e98710e50d8893f4c2d5c7a4741a02f00b4f9ce6d1b7d3a90c3d2737e", "fetched_at": "2026-07-12T02:37:35.733Z", "recordings": [ { "recording_id": "5b7ff56e0d631a8b9b2e9d0317efe17e831aab376e830f7ca53bfd1b5f87f8f8", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/15f/15ff2abca2073a4a384bf47d8daa3cbf476c0205ae0b5b50f28fff565f40eb0d.mp3", "archive_relative_path": "raw/audio/15f/15ff2abca2073a4a384bf47d8daa3cbf476c0205ae0b5b50f28fff565f40eb0d.mp3" } ] } ], "prediction": "Tami etlugowaqan?", "reference": "Tami e'jnt etlugwet?" }, { "id": "mic-sent-5444fb358bb29a771677db5e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she turned his/her boat quickly.", "output_text": "Jaqal(i)gawasgeget na ugtul.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she turned his/her boat quickly.", "mic_Latn": "Jaqal(i)gawasgeget na ugtul." }, "canonical_ref": "entries/g/gawasgeget/gawasgeget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a776232da341319cade7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gawasgeget/gawasgeget.html", "entry_url": "https://mikmaqonline.org/entries/g/gawasgeget/gawasgeget.html", "headword": "gawasgeget", "example_index": 0, "raw_html_path": "raw/entries/11316e5a06ff9cfd67d40fdda7834d8e7731de99dfd172ff20491877786c5c09.html", "raw_html_sha256": "ff02fcd63fdec94585b555eea16460dcee1f7fa41dcf63744165d55d3f9ba90d", "fetched_at": "2026-07-12T02:38:46.430Z", "recordings": [ { "recording_id": "7ca6903a024661d7737f6cd0e4323dcd828e4c57abbc74da760e8033c7574cff", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d74/d744a5bad2d41cf49bde284162896e4d6e1937acc6a68f334e794b5bc193345a.mp3", "archive_relative_path": "raw/audio/d74/d744a5bad2d41cf49bde284162896e4d6e1937acc6a68f334e794b5bc193345a.mp3" } ] } ], "prediction": "Gi's gesatg ugtaqan ugjit.", "reference": "Jaqal(i)gawasgeget na ugtul." }, { "id": "mic-sent-5448de78cef9d792ef5af1c3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where did you get the Native ones?", "output_text": "Nnueie'g tam weja'les'pnig?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where did you get the Native ones?", "mic_Latn": "Nnueie'g tam weja'les'pnig?" }, "canonical_ref": "entries/l/lnueiei/lnueiei.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-742bfe310c16bf18842f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lnueiei/lnueiei.html", "entry_url": "https://mikmaqonline.org/entries/l/lnueiei/lnueiei.html", "headword": "lnueiei", "example_index": 1, "raw_html_path": "raw/entries/cc51c3f46d5d7c8fa4a4d6da347c4447768b56faf1d2db6f3df42f034d580e41.html", "raw_html_sha256": "5faceb48be7f5a05b885f7ee0e43119e2b639b1e1586328efda5f0d5d9f644dd", "fetched_at": "2026-07-12T02:40:36.700Z", "recordings": [ { "recording_id": "49799d7a169f373a17a536b26ee380667dbda024bc5c4ab2ab7cbec00eb743fc", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/613/613381e59dfdc31bce28dabd9b8bf5d21fbfb03dbf1a0246c98ff46414aeeca4.mp3", "archive_relative_path": "raw/audio/613/613381e59dfdc31bce28dabd9b8bf5d21fbfb03dbf1a0246c98ff46414aeeca4.mp3" } ] }, { "entry_id": "entries/n/nnueiei/nnueiei.html", "entry_url": "https://mikmaqonline.org/entries/n/nnueiei/nnueiei.html", "headword": "nnueiei", "example_index": 1, "raw_html_path": "raw/entries/7142cea8eb8e49f51bbd8a3be7415af58d872d8d56915b8f038fb66f11cfd840.html", "raw_html_sha256": "d6b5f6672f096208d8ed1eda89a3667b2b41c20a3d86d991f52788fa81918f1f", "fetched_at": "2026-07-12T02:42:41.240Z", "recordings": [ { "recording_id": "699a8267bf5ec79ef3c6f94d83296895ae130f4cbaa8405362cfd8b8a1fa7fd2", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/613/613381e59dfdc31bce28dabd9b8bf5d21fbfb03dbf1a0246c98ff46414aeeca4.mp3", "archive_relative_path": "raw/audio/613/613381e59dfdc31bce28dabd9b8bf5d21fbfb03dbf1a0246c98ff46414aeeca4.mp3" } ] } ], "prediction": "Tami te's'tmi'j na Nmu'j?", "reference": "Nnueie'g tam weja'les'pnig?" }, { "id": "mic-sent-54bc28242eb2012631b6ea31:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I wonder which dog impregnated my dog.", "output_text": "Mu' gejiam'g ta'n tegen nmu'j gisteluaqtl nti'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I wonder which dog impregnated my dog.", "mic_Latn": "Mu' gejiam'g ta'n tegen nmu'j gisteluaqtl nti'l." }, "canonical_ref": "entries/g/gisteluatl/gisteluatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-51d37e0e73919ebddbf3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gisteluatl/gisteluatl.html", "entry_url": "https://mikmaqonline.org/entries/g/gisteluatl/gisteluatl.html", "headword": "gisteluatl", "example_index": 0, "raw_html_path": "raw/entries/ffbf322426a70f6e45e0a46197018532afc8f439660368b770d72b3acd923fb4.html", "raw_html_sha256": "e5e806cf4003f8d90baa7bd51088753be384e0ec6c37c51731cf89b585b7f9d5", "fetched_at": "2026-07-12T02:39:43.285Z", "recordings": [ { "recording_id": "a1a978d55a562523d213de570e8e04d9a57efc786c430f8e7ca79c00383cf08f", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/aa3/aa335899d4f2e00056e211791eeb353b629814fe3c78be600204a994d35a45c3.mp3", "archive_relative_path": "raw/audio/aa3/aa335899d4f2e00056e211791eeb353b629814fe3c78be600204a994d35a45c3.mp3" } ] } ], "prediction": "Ta'n goqwei ta'n te's'g nmu'ji'j.", "reference": "Mu' gejiam'g ta'n tegen nmu'j gisteluaqtl nti'l." }, { "id": "mic-sent-56c9e57faf2b6f1dc9be4b77:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My hip is bothering me today.", "output_text": "Gisgug we'tuguwig ntmepigajm.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My hip is bothering me today.", "mic_Latn": "Gisgug we'tuguwig ntmepigajm." }, "canonical_ref": "entries/u/upmepigaj/upmepigaj.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c3e7b1f44c602c952187", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/upmepigaj/upmepigaj.html", "entry_url": "https://mikmaqonline.org/entries/u/upmepigaj/upmepigaj.html", "headword": "upmepigaj", "example_index": 0, "raw_html_path": "raw/entries/a045e2aac8a443933ea1833b5870d91bb692514c45710847a24f76e1e463cb5a.html", "raw_html_sha256": "d115308d07d6d47fdf785be313e5a64d43b7929f9595f55f7b329a9c0f4c7100", "fetched_at": "2026-07-12T02:46:26.562Z", "recordings": [ { "recording_id": "f176c5c2e8789bd098e83754dd27fc877b79d71e36cdeb28f47dd6ad837238b3", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/03f/03fd6df14db6b28ef021c4764b4348d229c1e8b8daf602d31afe0fd399362e92.mp3", "archive_relative_path": "raw/audio/03f/03fd6df14db6b28ef021c4764b4348d229c1e8b8daf602d31afe0fd399362e92.mp3" } ] } ], "prediction": "Pugwelg na ntus gisgug.", "reference": "Gisgug we'tuguwig ntmepigajm." }, { "id": "mic-sent-58b5c9dd6fbe804eae395684:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is pulling on his/her boat while he/she is going along the shore.", "output_text": "Wesuw'tqang ugtul ge's pemjajiga'sij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is pulling on his/her boat while he/she is going along the shore.", "mic_Latn": "Wesuw'tqang ugtul ge's pemjajiga'sij." }, "canonical_ref": "entries/w/wesuw'tqang/wesuw'tqang.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7a2b245abb86db61ce80", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wesuw'tqang/wesuw'tqang.html", "entry_url": "https://mikmaqonline.org/entries/w/wesuw'tqang/wesuw'tqang.html", "headword": "wesuw'tqang", "example_index": 0, "raw_html_path": "raw/entries/e32797635465cdefe6f54a856a35cc0a44c2321bf223a979a7c40f3b258dce5c.html", "raw_html_sha256": "bdc47a7d873e80f84e24b9648887c92792875c186b9d4bb0ba281377bfadf4b7", "fetched_at": "2026-07-12T02:47:22.874Z", "recordings": [ { "recording_id": "d735df3484fdefedec44605be5263b52d6b0a59fb1b721798c7eb5abd03b6466", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f0e/f0e2e76db2b0d0d9b4dbb683bce46a326ba5c57729c647269cf53208635af2ed.mp3", "archive_relative_path": "raw/audio/f0e/f0e2e76db2b0d0d9b4dbb683bce46a326ba5c57729c647269cf53208635af2ed.mp3" } ] } ], "prediction": "Gesatg ugta'latl ta'n tujiw eliei.", "reference": "Wesuw'tqang ugtul ge's pemjajiga'sij." }, { "id": "mic-sent-58d314fb6c265c24f79115f7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's snowing heavily from the cove to Matapidia.", "output_text": "Gesigawipsaq weja'tegemg wanne'g glapis Matawe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's snowing heavily from the cove to Matapidia.", "mic_Latn": "Gesigawipsaq weja'tegemg wanne'g glapis Matawe'g." }, "canonical_ref": "entries/w/weja'tegemg/weja'tegemg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b78dbdf0b0cc14f712df", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/weja'tegemg/weja'tegemg.html", "entry_url": "https://mikmaqonline.org/entries/w/weja'tegemg/weja'tegemg.html", "headword": "weja'tegemg", "example_index": 0, "raw_html_path": "raw/entries/07cc921e7a4a4c57ad88ec6d80d570b3f9102c9aad911c1116d39d1b3d2a2b24.html", "raw_html_sha256": "22f370908e05e3ce7fcf4961ebf15eba29dfb330a2ac0293e2386be7c7853623", "fetched_at": "2026-07-12T02:46:48.478Z", "recordings": [ { "recording_id": "a1dee9bf9ec24ba1c549a57776b366c18b8d8d3a95c8d38f5b702e29b25e64df", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1a3/1a350bc7593a5de0e7d19d4d02a9adc04b93e3ed09212f13640282e8281148c5.mp3", "archive_relative_path": "raw/audio/1a3/1a350bc7593a5de0e7d19d4d02a9adc04b93e3ed09212f13640282e8281148c5.mp3" } ] } ], "prediction": "Pugwelg ta'n tujiw gisijig Matapidia.", "reference": "Gesigawipsaq weja'tegemg wanne'g glapis Matawe'g." }, { "id": "mic-sent-59723d58244251ebf7900140:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Peter tells Mary Ann everything.", "output_text": "Piel agnutmuatl Mali A'nnal ms't goqwei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Peter tells Mary Ann everything.", "mic_Latn": "Piel agnutmuatl Mali A'nnal ms't goqwei." }, "canonical_ref": "entries/a/agnutmuatl/agnutmuatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1fad15eadf60b4d5f143", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/agnutmuatl/agnutmuatl.html", "entry_url": "https://mikmaqonline.org/entries/a/agnutmuatl/agnutmuatl.html", "headword": "agnutmuatl", "example_index": 0, "raw_html_path": "raw/entries/2921a09a81ad28f35d7d464425dbf063717c22dee0ba3fc440dbb282c0f6c30c.html", "raw_html_sha256": "dff03d8cc552d489febb8143eeb439b2b38ccb347d19d0c8942f5c65802e3ef5", "fetched_at": "2026-07-12T02:36:31.082Z", "recordings": [ { "recording_id": "fc3c551562b7e0b5390be2baa3eb53e3daf289872934b1514c70005f321d48ec", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/513/513519bace41de40bded91afabe5875a1ee3b5b81ca7ec7333e008ec5088dcea.mp3", "archive_relative_path": "raw/audio/513/513519bace41de40bded91afabe5875a1ee3b5b81ca7ec7333e008ec5088dcea.mp3" } ] } ], "prediction": "Pie'l telimatl Malia'n ms't goqwei.", "reference": "Piel agnutmuatl Mali A'nnal ms't goqwei." }, { "id": "mic-sent-599783591a6bcc0cfbd90e4a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "If you put it too close to there it will sink in.", "output_text": "Wesua'q na gigji'w iga'tu'n na'te'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "If you put it too close to there it will sink in.", "mic_Latn": "Wesua'q na gigji'w iga'tu'n na'te'l." }, "canonical_ref": "entries/w/wesua'q/wesua'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-efb7d430c6e03270cf5c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wesua'q/wesua'q.html", "entry_url": "https://mikmaqonline.org/entries/w/wesua'q/wesua'q.html", "headword": "wesua'q", "example_index": 0, "raw_html_path": "raw/entries/ce22b794bd477176a28943cbb2248fbe9512882b7d288f331a1a232f7c3b7b6a.html", "raw_html_sha256": "6676ed4cf39a4ef285760aad0f881198a7b60454b699095e5cad8c918d760b5d", "fetched_at": "2026-07-12T02:47:21.066Z", "recordings": [ { "recording_id": "8c8210d43051045adefb5a5a72f7b8a31f2b404f1824c924bed275e753fb3fd9", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4af/4afc5089d62969ddccae54adfc4a6d9b9b6221650c3ad719a7d04e85d8e9f1a7.mp3", "archive_relative_path": "raw/audio/4af/4afc5089d62969ddccae54adfc4a6d9b9b6221650c3ad719a7d04e85d8e9f1a7.mp3" } ] } ], "prediction": "Gi's gesatg na te'sipow.", "reference": "Wesua'q na gigji'w iga'tu'n na'te'l." }, { "id": "mic-sent-5a89271dfacebda2bff6a2d1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "These are new photographs, when were they changed?", "output_text": "Pile'g ula napui'gigng, ta'n sa'se'wa'tasisnig?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "These are new photographs, when were they changed?", "mic_Latn": "Pile'g ula napui'gigng, ta'n sa'se'wa'tasisnig?" }, "canonical_ref": "entries/s/sa'se'wa'tasit/sa'se'wa'tasit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-56e694beed441dc65d45", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sa'se'wa'tasit/sa'se'wa'tasit.html", "entry_url": "https://mikmaqonline.org/entries/s/sa'se'wa'tasit/sa'se'wa'tasit.html", "headword": "sa'se'wa'tasit", "example_index": 0, "raw_html_path": "raw/entries/05bc09b8d4015036419cbf16e3655e1b5f7951765eab4e2e26d0334bdb796b7d.html", "raw_html_sha256": "33a5306cd48491f754091f875ec6d3214a65bcf76a4a4a3af9e1af28ee7d8a70", "fetched_at": "2026-07-12T02:36:19.495Z", "recordings": [ { "recording_id": "138c375e10592b06a27287ec380a3b277fb310d7171ceea767cff013a1f23341", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c66/c662148f3597c7c9796545c5000a3e53e74b0ead094245b5566fd801e35d6392.mp3", "archive_relative_path": "raw/audio/c66/c662148f3597c7c9796545c5000a3e53e74b0ead094245b5566fd801e35d6392.mp3" } ] } ], "prediction": "Pilei'g ula pilei, ta'n tujiw pas'g?", "reference": "Pile'g ula napui'gigng, ta'n sa'se'wa'tasisnig?" }, { "id": "mic-sent-5b1a17f49cb9e4fb72e2a73c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Bee bee pellets are all over the place, I expect many things were used as targets.", "output_text": "Sqolu'sguji'jl telialagwegl, miamuj gaqatepiaq ta'n goqwei gisipe'sgas'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Bee bee pellets are all over the place, I expect many things were used as targets.", "mic_Latn": "Sqolu'sguji'jl telialagwegl, miamuj gaqatepiaq ta'n goqwei gisipe'sgas'g." }, "canonical_ref": "entries/s/sqolu'sguji'j/sqolu'sguji'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8644a5bff2cfba27e931", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sqolu'sguji'j/sqolu'sguji'j.html", "entry_url": "https://mikmaqonline.org/entries/s/sqolu'sguji'j/sqolu'sguji'j.html", "headword": "sqolu'sguji'j", "example_index": 0, "raw_html_path": "raw/entries/15a8c4b161a5354c26a5e8d04cb7170a5f19c8b9b2cb32d7ec1ba98e7e192cb6.html", "raw_html_sha256": "8ab4286a026196302610cc5d7223ffba761054942c354389f2f77c05ccff164d", "fetched_at": "2026-07-12T02:45:14.804Z", "recordings": [ { "recording_id": "b59cecdb05eee63b3dcc1f6a9f3381bc3dda5513e9d760f41a5901df576d184d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1cc/1cc185d11bbf8d2cced843c6de4d658a83ec64c38c61620866d0c19e038a6192.mp3", "archive_relative_path": "raw/audio/1cc/1cc185d11bbf8d2cced843c6de4d658a83ec64c38c61620866d0c19e038a6192.mp3" } ] } ], "prediction": "Pugwelg'p'g ta'n te's'g, telte'lm na ms't goqwei etlmisga'toq.", "reference": "Sqolu'sguji'jl telialagwegl, miamuj gaqatepiaq ta'n goqwei gisipe'sgas'g." }, { "id": "mic-sent-5b4847fe16e11c2476fd03de:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The staff at that store are friendly.", "output_text": "Ni'lajo'ltijig na etlnussaqig'tijig na magasang.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The staff at that store are friendly.", "mic_Latn": "Ni'lajo'ltijig na etlnussaqig'tijig na magasang." }, "canonical_ref": "entries/n/ni'laje'g/ni'laje'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-82fe6498b2f4866a5979", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ni'laje'g/ni'laje'g.html", "entry_url": "https://mikmaqonline.org/entries/n/ni'laje'g/ni'laje'g.html", "headword": "ni'laje'g", "example_index": 0, "raw_html_path": "raw/entries/b6dc3691527ef3b5348fb116725a9d5dc722d9a99141ea646a22288e0ce88ca5.html", "raw_html_sha256": "f050d0836ad7c4946505f431e787de8a861053e72842bf076ba8b104b5a49905", "fetched_at": "2026-07-12T02:42:33.818Z", "recordings": [ { "recording_id": "e57f998d7a7fa45e33bece0cbdaf1756e7ee830af4dcb5a64a3240fda3202b2c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e77/e771d9110b63baca726c9f1565f52561462d048cc92d201151f5a023fe666a11.mp3", "archive_relative_path": "raw/audio/e77/e771d9110b63baca726c9f1565f52561462d048cc92d201151f5a023fe666a11.mp3" } ] } ], "prediction": "We'gwi'jig na lugowaqan na we'gwigsit.", "reference": "Ni'lajo'ltijig na etlnussaqig'tijig na magasang." }, { "id": "mic-sent-5b69cd9f167de3f9532cdcac:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Just pour a little bit of water.", "output_text": "Pas'g ta's'ji'jg samuqwan lguta'tu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Just pour a little bit of water.", "mic_Latn": "Pas'g ta's'ji'jg samuqwan lguta'tu." }, "canonical_ref": "entries/t/ta's'ji'jg/ta's'ji'jg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9f4dcab0b68b225632e4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/ta's'ji'jg/ta's'ji'jg.html", "entry_url": "https://mikmaqonline.org/entries/t/ta's'ji'jg/ta's'ji'jg.html", "headword": "ta's'ji'jg", "example_index": 0, "raw_html_path": "raw/entries/f5004a12fbc0229deb0f4a3ca89a1020685500217b4aed50962757acd272dcb1.html", "raw_html_sha256": "4d45c9c73eaeb19f51e3010aa71133c13688cf97ae84c58b0cbbc42d81beb269", "fetched_at": "2026-07-12T02:45:26.159Z", "recordings": [ { "recording_id": "7559ab09176e8b53f29be17ee500aca034ed6b8b3b290077e89d511eea436bcd", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/424/42403b5ed3d93cffe420aeb78e5e0c5e0e54f86a9ad364522e74daba9291173a.mp3", "archive_relative_path": "raw/audio/424/42403b5ed3d93cffe420aeb78e5e0c5e0e54f86a9ad364522e74daba9291173a.mp3" } ] } ], "prediction": "Pas'g newte'ji'j glapis'g.", "reference": "Pas'g ta's'ji'jg samuqwan lguta'tu." }, { "id": "mic-sent-5c08b77600977e6a683d4dac:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she puts his/her boat in drydock every winter.", "output_text": "Oqtatqa'toq ugtul te's gesig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she puts his/her boat in drydock every winter.", "mic_Latn": "Oqtatqa'toq ugtul te's gesig." }, "canonical_ref": "entries/o/oqtatqa'toq/oqtatqa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5cf2f53396e83ad05694", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/o/oqtatqa'toq/oqtatqa'toq.html", "entry_url": "https://mikmaqonline.org/entries/o/oqtatqa'toq/oqtatqa'toq.html", "headword": "oqtatqa'toq", "example_index": 0, "raw_html_path": "raw/entries/c841d607cbeacc76f3af180877ce74edf5ee89eb2ee93d94745b1f9d5837e983.html", "raw_html_sha256": "586213a1bd793d4bd39535eea7886303185d500329ca13944e1a9283c0250ba4", "fetched_at": "2026-07-12T02:43:02.771Z", "recordings": [ { "recording_id": "3cb3406416f47ddbd3e0de2875abc8938443c5bbb650f27683c9b6e6459ef218", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c34/c34e57f8cdfd08c8f27046dffc3504867b0a79a521fc3a2ce34b6f395b3a54b6.mp3", "archive_relative_path": "raw/audio/c34/c34e57f8cdfd08c8f27046dffc3504867b0a79a521fc3a2ce34b6f395b3a54b6.mp3" } ] } ], "prediction": "Te's'g ugta'latl ugtaqan te'sipu'g.", "reference": "Oqtatqa'toq ugtul te's gesig." }, { "id": "mic-sent-5c3ba57f29e061c7a3faa894:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You'll need more than one blueberry if you want to make a pie.", "output_text": "Me' aq newte' pguman nuta'tes gtuitu'n petaqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You'll need more than one blueberry if you want to make a pie.", "mic_Latn": "Me' aq newte' pguman nuta'tes gtuitu'n petaqan." }, "canonical_ref": "entries/p/pguman/pguman.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a00df708a9d0728644a6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pguman/pguman.html", "entry_url": "https://mikmaqonline.org/entries/p/pguman/pguman.html", "headword": "pguman", "example_index": 0, "raw_html_path": "raw/entries/640b945b137cc75f6b1b393be64047ab69e803d94f8466e23933a122d9631666.html", "raw_html_sha256": "f3dc8dac32c3680b018836148e53e1a5c7d61bc327b1e4e1d31b4feaf0e75989", "fetched_at": "2026-07-12T02:43:51.914Z", "recordings": [ { "recording_id": "6a81e33040e9af63c44fed171cd19fe47169925372ef6e0edafde155d6e55eaa", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c93/c9377ca6836e9a095381c87fe91d2efeffd00dc0e290e73f44967037419cc78c.mp3", "archive_relative_path": "raw/audio/c93/c9377ca6836e9a095381c87fe91d2efeffd00dc0e290e73f44967037419cc78c.mp3" } ] } ], "prediction": "Me' ms't newte'g gmu'ji'j ta'n tujiw glapis.", "reference": "Me' aq newte' pguman nuta'tes gtuitu'n petaqan." }, { "id": "mic-sent-5cf3dfc6262c6c5435c255af:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I have to medicate myself, this cold does not want to leave me.", "output_text": "Amujpa nepisi, ula tgei mu getu' punajeiwigw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I have to medicate myself, this cold does not want to leave me.", "mic_Latn": "Amujpa nepisi, ula tgei mu getu' punajeiwigw." }, "canonical_ref": "entries/n/nepisit/nepisit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-592ea06739cf92627ca3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nepisit/nepisit.html", "entry_url": "https://mikmaqonline.org/entries/n/nepisit/nepisit.html", "headword": "nepisit", "example_index": 0, "raw_html_path": "raw/entries/572f17f9a70e82c0ea7b8bd964657a38e76eea28a68efb26f64f135be33a539e.html", "raw_html_sha256": "44683c79354986ea881ad66f766a0e6b0ec5a479b282bc9949ae793721b182a0", "fetched_at": "2026-07-12T02:42:21.035Z", "recordings": [ { "recording_id": "f4fa5cc63b281bdf2dd3c81eebaea27d0a895a281d867195324938e3d2ade58f", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/99b/99bf575644b87a2ccd7301a42266329fc1e0110c2dea9801ab861098038992a1.mp3", "archive_relative_path": "raw/audio/99b/99bf575644b87a2ccd7301a42266329fc1e0110c2dea9801ab861098038992a1.mp3" } ] } ], "prediction": "Amujpa ni'n amujpa'toq, ula gmu'tmu'j ma' negm.", "reference": "Amujpa nepisi, ula tgei mu getu' punajeiwigw." }, { "id": "mic-sent-5d3e1ee51a1e8fd3dedcf7b8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The boy looks about for his father.", "output_text": "Lpa'tuj alamatl ujjl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The boy looks about for his father.", "mic_Latn": "Lpa'tuj alamatl ujjl." }, "canonical_ref": "entries/a/alamatl/alamatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0e1d8574f989c0122e74", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/alamatl/alamatl.html", "entry_url": "https://mikmaqonline.org/entries/a/alamatl/alamatl.html", "headword": "alamatl", "example_index": 0, "raw_html_path": "raw/entries/1554a6e1aa91600836768b3d6b0af836b0c636e31f7f0996277e506583fa83a1.html", "raw_html_sha256": "44aa6c399467a87bc0d59b3687bfa64301e7945f6ae8701a84194ce03bf904f2", "fetched_at": "2026-07-12T02:36:34.290Z", "recordings": [ { "recording_id": "7554896d701f1842594657885b0386bd7aa28b5dadb8b62cb1de0cd93d6de387", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dc4/dc400a8184a62701b60c323d694cd1dbc4e9d0eb8f9e86401116febd725d0cef.mp3", "archive_relative_path": "raw/audio/dc4/dc400a8184a62701b60c323d694cd1dbc4e9d0eb8f9e86401116febd725d0cef.mp3" } ] } ], "prediction": "Lpa'tuj gesatg ugjig.", "reference": "Lpa'tuj alamatl ujjl." }, { "id": "mic-sent-5d64d1d9c12e4791157751c3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That person is devilish.", "output_text": "Mntuit na ta'n wen.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That person is devilish.", "mic_Latn": "Mntuit na ta'n wen." }, "canonical_ref": "entries/m/mntuit/mntuit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c3a1aa3bf47604ee2790", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mntuit/mntuit.html", "entry_url": "https://mikmaqonline.org/entries/m/mntuit/mntuit.html", "headword": "mntuit", "example_index": 0, "raw_html_path": "raw/entries/a8e30fc18cd238d184d4adb98ff36f76be6e7a8a9cb65e9ecd8af00c3ae4112b.html", "raw_html_sha256": "749feb259387bf3fc25a87b5b4e944fddac9eff1dc11b329f2b6ca0a23550d6a", "fetched_at": "2026-07-12T02:41:44.733Z", "recordings": [ { "recording_id": "7c23d3e12cb3e4bbfc64fd3f0700dbcf6323099dae119a841e96394106a5d113", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/593/5931d4e4ab91769bf0e2912f2fe50fb2d405082e4194179d6d3518e28e99f014.mp3", "archive_relative_path": "raw/audio/593/5931d4e4ab91769bf0e2912f2fe50fb2d405082e4194179d6d3518e28e99f014.mp3" } ] } ], "prediction": "We'gwi'g na ji'nm.", "reference": "Mntuit na ta'n wen." }, { "id": "mic-sent-5dfd63c63e41ead46035608e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary fell and bloodied her head.", "output_text": "Mali gisimaltewtestoq unji.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary fell and bloodied her head.", "mic_Latn": "Mali gisimaltewtestoq unji." }, "canonical_ref": "entries/m/maltewtestoq/maltewtestoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f154d40f1a9113b09d7c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/maltewtestoq/maltewtestoq.html", "entry_url": "https://mikmaqonline.org/entries/m/maltewtestoq/maltewtestoq.html", "headword": "maltewtestoq", "example_index": 0, "raw_html_path": "raw/entries/8ecd2c99cc0a9dba159534cec738d09cf45a846f7cb32fe779812464140f77fc.html", "raw_html_sha256": "17a4c1cfcdb188293b72b872b889fb0446212ab0d4be243e9db9ab9181e4d2d5", "fetched_at": "2026-07-12T02:40:47.548Z", "recordings": [ { "recording_id": "af482ed7e95d26f6528507b4aa5330216180956df7836eb89c74f7ad0944674f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7ec/7ec7cc5b9f632d3390a059c830f958e211ef14729b684b378c718b98a4393108.mp3", "archive_relative_path": "raw/audio/7ec/7ec7cc5b9f632d3390a059c830f958e211ef14729b684b378c718b98a4393108.mp3" } ] } ], "prediction": "Mali gesatg aq gesga'toq ugjit.", "reference": "Mali gisimaltewtestoq unji." }, { "id": "mic-sent-5e4815e4bc726a52d596632f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Yes I heard about it, how about you, have you heard yet?", "output_text": "Nutmaiap e'e, gatu gi'l, gi's nutman?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Yes I heard about it, how about you, have you heard yet?", "mic_Latn": "Nutmaiap e'e, gatu gi'l, gi's nutman?" }, "canonical_ref": "entries/n/nutmat/nutmat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-46592f57de43985f5c84", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nutmat/nutmat.html", "entry_url": "https://mikmaqonline.org/entries/n/nutmat/nutmat.html", "headword": "nutmat", "example_index": 0, "raw_html_path": "raw/entries/c6b1ae8e1e236c4f61dea471d1981da227c71db8b9e1f9685962885c5fa2be7a.html", "raw_html_sha256": "92448732c6af52a681461fd5778e4cfdd889b95bad830ba1f94fbef7e8a292a0", "fetched_at": "2026-07-12T02:42:57.527Z", "recordings": [ { "recording_id": "20c17d66696f6728fcf2c28a7974274e9599521cfcec60232398a6db290d2eb9", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/576/576e2eb50992d507858e757497c57bca3375331bb8aeeb33cd3a466d7a315cdf.mp3", "archive_relative_path": "raw/audio/576/576e2eb50992d507858e757497c57bca3375331bb8aeeb33cd3a466d7a315cdf.mp3" } ] } ], "prediction": "E'e's nugu' telte'l, goqwei etug, gi's gi'l te's'g?", "reference": "Nutmaiap e'e, gatu gi'l, gi's nutman?" }, { "id": "mic-sent-5e7d29e61227be6adb4a03f1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My, the wind is from the north today!", "output_text": "We'gwioqwatg gisgug!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My, the wind is from the north today!", "mic_Latn": "We'gwioqwatg gisgug!" }, "canonical_ref": "entries/o/oqwatg/oqwatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6d909c3b5fdf46afb719", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/o/oqwatg/oqwatg.html", "entry_url": "https://mikmaqonline.org/entries/o/oqwatg/oqwatg.html", "headword": "oqwatg", "example_index": 0, "raw_html_path": "raw/entries/19b821fcdbe439dbf701fe50da94cc263e6892f87eb0eb473ebcebc97bd025ba.html", "raw_html_sha256": "47c8b3000e632d8c234acb1bd28d244e2471766d58429a9ff2197e963b67ae3d", "fetched_at": "2026-07-12T02:43:03.177Z", "recordings": [ { "recording_id": "d7881dd1ab04f4ddabdcae54ff6ad572866d53e1727578f433e620ce26cc4d87", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/41f/41f80fa45545a72a2edce7f58fdbd3ed904e95ccabb304c44fe5aa87f4cc3b6c.mp3", "archive_relative_path": "raw/audio/41f/41f80fa45545a72a2edce7f58fdbd3ed904e95ccabb304c44fe5aa87f4cc3b6c.mp3" } ] } ], "prediction": "Me' gisgug gisgm'g!", "reference": "We'gwioqwatg gisgug!" }, { "id": "mic-sent-5ec6335ee85b5e64f329e4e7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is a healer, and he/she is a good healer.", "output_text": "Negm nepiteget, aq natawinpiteget.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is a healer, and he/she is a good healer.", "mic_Latn": "Negm nepiteget, aq natawinpiteget." }, "canonical_ref": "entries/n/nepiteget/nepiteget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-55a4655cb67ed9c7acd0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nepiteget/nepiteget.html", "entry_url": "https://mikmaqonline.org/entries/n/nepiteget/nepiteget.html", "headword": "nepiteget", "example_index": 0, "raw_html_path": "raw/entries/d8e0b53c27af10ac02bc786ff91accf683cda566c1a97b449beb641874a54572.html", "raw_html_sha256": "123fcf64bf8cd78179df48e4e28035e11eeec60fd1e1059e1a0470d001e0fb15", "fetched_at": "2026-07-12T02:42:21.148Z", "recordings": [ { "recording_id": "2c8cf8e5b9e032bb9132ccddeb24ce80424be529073ae67182976213a2d0e78e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0a2/0a2b1fb399469e5aab910ff851dc7097e78bda406d26330cc3810710ca064c94.mp3", "archive_relative_path": "raw/audio/0a2/0a2b1fb399469e5aab910ff851dc7097e78bda406d26330cc3810710ca064c94.mp3" } ] } ], "prediction": "We'gwi'jig, aq we'gwig.", "reference": "Negm nepiteget, aq natawinpiteget." }, { "id": "mic-sent-5f6e380d1346e98e9156fd88:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Black ash is used when making a basket.", "output_text": "Wisqoq na e'wut ligpnign eltmg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Black ash is used when making a basket.", "mic_Latn": "Wisqoq na e'wut ligpnign eltmg." }, "canonical_ref": "entries/w/wisqoq/wisqoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a39b6c3d8e278dc452a0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wisqoq/wisqoq.html", "entry_url": "https://mikmaqonline.org/entries/w/wisqoq/wisqoq.html", "headword": "wisqoq", "example_index": 0, "raw_html_path": "raw/entries/44af8e41f0e67a7520ef038ce1aff1800453bf045f0fd7734f778f090ca58ded.html", "raw_html_sha256": "b77a24ec3bc5c0ad1e461b384a75848059be3e6a48c9246dc8eb5a6ab9464e3c", "fetched_at": "2026-07-12T02:47:40.459Z", "recordings": [ { "recording_id": "e040eb1246ead1102745315fb790c218e8733d85cecf012314d622d75e332c77", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/910/9105b1ef8d9a7ae243d4e79a1e93e1758aba53f82db607f9c02f696fa270cce0.mp3", "archive_relative_path": "raw/audio/910/9105b1ef8d9a7ae243d4e79a1e93e1758aba53f82db607f9c02f696fa270cce0.mp3" } ] } ], "prediction": "Negamgwi'g etlmisga'toq ta'n tujiw gesgm'g.", "reference": "Wisqoq na e'wut ligpnign eltmg." }, { "id": "mic-sent-6049238c2086d1b7e1db7604:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What's standing over there?", "output_text": "Goqwei gaqamig ala tet?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What's standing over there?", "mic_Latn": "Goqwei gaqamig ala tet?" }, "canonical_ref": "entries/g/gaqamig/gaqamig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b505c6d829bdee331275", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gaqamig/gaqamig.html", "entry_url": "https://mikmaqonline.org/entries/g/gaqamig/gaqamig.html", "headword": "gaqamig", "example_index": 0, "raw_html_path": "raw/entries/553483cd257b5a545103929865234fb159d4d5c6e8b4ec8ade1bd2d3e49b8661.html", "raw_html_sha256": "e240e1c1490d17b1269d812df5e50e7aeae39ea7cb4211e602f7f782023dc5d6", "fetched_at": "2026-07-12T02:38:38.175Z", "recordings": [ { "recording_id": "79089ac637ba8f584240152469bd97cebb9eb2c4b043e684580058180877b66c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d7d/d7da8329d4c1170e019db10c72d7f0091d80649a3f0ae0602eb20f3d50170833.mp3", "archive_relative_path": "raw/audio/d7d/d7da8329d4c1170e019db10c72d7f0091d80649a3f0ae0602eb20f3d50170833.mp3" } ] } ], "prediction": "Goqwei ta'n te'sipow?", "reference": "Goqwei gaqamig ala tet?" }, { "id": "mic-sent-609e38d5a3d43bf4b5b3f049:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I can't go shopping therefore you go.", "output_text": "Ma ni'n gisnatanguaw glaman gi'l lia.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I can't go shopping therefore you go.", "mic_Latn": "Ma ni'n gisnatanguaw glaman gi'l lia." }, "canonical_ref": "entries/g/glaman/glaman.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b32ad83d5867ce2dea59", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/glaman/glaman.html", "entry_url": "https://mikmaqonline.org/entries/g/glaman/glaman.html", "headword": "glaman", "example_index": 0, "raw_html_path": "raw/entries/8d7e40c2bc3964cb8463cf0f8370740da9c14c96b3a93b79c5905fa13d4e6436.html", "raw_html_sha256": "7aed8571f392d11703cf8a13bf62dc895e18dd01d514ae24c3aad33097fec127", "fetched_at": "2026-07-12T02:39:49.312Z", "recordings": [ { "recording_id": "38f397dea6c69003004ea7db1c7bf3eab3b007ad1cd7ea99b27843098174b5fd", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cfd/cfd753ffe3a283bb6519a893efaed4dbaf1da1625918533ec83ce2594aa32aab.mp3", "archive_relative_path": "raw/audio/cfd/cfd753ffe3a283bb6519a893efaed4dbaf1da1625918533ec83ce2594aa32aab.mp3" } ] } ], "prediction": "Mu ni'n goqwei'g ta'n tujiw tlia'tu.", "reference": "Ma ni'n gisnatanguaw glaman gi'l lia." }, { "id": "mic-sent-610e3d9220b334af1049e210:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That was a close call for that little boy, he almost got hit.", "output_text": "Wejue'g na lpa'tu'ji'j, suel migutesgut.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That was a close call for that little boy, he almost got hit.", "mic_Latn": "Wejue'g na lpa'tu'ji'j, suel migutesgut." }, "canonical_ref": "entries/w/wejue'g/wejue'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-77e24b4c7f9f4b7795e4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejue'g/wejue'g.html", "entry_url": "https://mikmaqonline.org/entries/w/wejue'g/wejue'g.html", "headword": "wejue'g", "example_index": 0, "raw_html_path": "raw/entries/e0a87cc1f08f5b9907e81398c53f505411cd73098f07adf8bc8bcafc1aef3b84.html", "raw_html_sha256": "17dd5b8c14c04c892fd98aeaa07d1c7d8ecbdf05098ef58e4bc0a59e3005acf3", "fetched_at": "2026-07-12T02:46:56.268Z", "recordings": [ { "recording_id": "70dee79b0fd2b6152d8645a0cd05ef26933c62d8b669d33d083bf8b32365f026", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d1b/d1b36cb39c6d7e51b4066b5ed4c3205ca0706d15b3824c1851c558d1612e5d50.mp3", "archive_relative_path": "raw/audio/d1b/d1b36cb39c6d7e51b4066b5ed4c3205ca0706d15b3824c1851c558d1612e5d50.mp3" } ] } ], "prediction": "Weji'jg na lpa lpa'tuj, pas'g gesatg.", "reference": "Wejue'g na lpa'tu'ji'j, suel migutesgut." }, { "id": "mic-sent-6139e7bbf4c9ef402a3380f2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Cover that child, he/she is getting cold.", "output_text": "Anguna na mijua'ji'j, pemitgiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Cover that child, he/she is getting cold.", "mic_Latn": "Anguna na mijua'ji'j, pemitgiet." }, "canonical_ref": "entries/p/pemitgiet/pemitgiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-95be1b20578ae5610a09", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemitgiet/pemitgiet.html", "entry_url": "https://mikmaqonline.org/entries/p/pemitgiet/pemitgiet.html", "headword": "pemitgiet", "example_index": 0, "raw_html_path": "raw/entries/4afd852506ab8aebeb8a1398652a057b89834756c80aeb5a9ba2818c26e6ae13.html", "raw_html_sha256": "f88dfde8c1ef8155bcdb8d467dfb29441c7088d5a57afa14f11be8a9d3c1df88", "fetched_at": "2026-07-12T02:43:33.927Z", "recordings": [ { "recording_id": "83456a34077dd46890a9b4ca2bf37f1d4a798bc6db5ea57968ea9d2a629d5850", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6f1/6f1d1c2365723a1982b053b7d02d2406fbf66c1a063eb1fb3e7caa387d57a967.mp3", "archive_relative_path": "raw/audio/6f1/6f1d1c2365723a1982b053b7d02d2406fbf66c1a063eb1fb3e7caa387d57a967.mp3" } ] } ], "prediction": "Gesatg na lpa'tuj, gesatg.", "reference": "Anguna na mijua'ji'j, pemitgiet." }, { "id": "mic-sent-615dc516500192c7a3778f93:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "All my brother has to do is haul firewood.", "output_text": "Ntjignam na pas'g telugwet nujatejo'toqol pugsugl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "All my brother has to do is haul firewood.", "mic_Latn": "Ntjignam na pas'g telugwet nujatejo'toqol pugsugl." }, "canonical_ref": "entries/n/nujatejo'toqol/nujatejo'toqol.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-663ef72320a1a011c291", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nujatejo'toqol/nujatejo'toqol.html", "entry_url": "https://mikmaqonline.org/entries/n/nujatejo'toqol/nujatejo'toqol.html", "headword": "nujatejo'toqol", "example_index": 0, "raw_html_path": "raw/entries/308a4edaa69a0fedcaf4c62cb14a86a3bfcbc93e6e386a91f902ec06b14927e4.html", "raw_html_sha256": "4e6aacfde72503e46c15c08257edea5e4fee1fa409ff903a3e9bc061f22a0c65", "fetched_at": "2026-07-12T02:42:47.570Z", "recordings": [ { "recording_id": "4fcb89fcd7c501898988d3ae074d66defc9be8c7ec9d219bb4abff5ca45be777", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/312/312472102267e316f413049f253cdde541a03505ae0b53bac2ea6cb7d6101a94.mp3", "archive_relative_path": "raw/audio/312/312472102267e316f413049f253cdde541a03505ae0b53bac2ea6cb7d6101a94.mp3" } ] } ], "prediction": "Pas'g amujpa ni'n nugu' nujga'toq.", "reference": "Ntjignam na pas'g telugwet nujatejo'toqol pugsugl." }, { "id": "mic-sent-61732cc3c75ce80534227f67:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary Ann spreads out her jacket to dry it out fast.", "output_text": "Mali'an sipelega'latl ugwesgitji'jml ugjit jaqalipiasinin.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary Ann spreads out her jacket to dry it out fast.", "mic_Latn": "Mali'an sipelega'latl ugwesgitji'jml ugjit jaqalipiasinin." }, "canonical_ref": "entries/s/sipelega'latl/sipelega'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-608e198e4fbaf344043a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sipelega'latl/sipelega'latl.html", "entry_url": "https://mikmaqonline.org/entries/s/sipelega'latl/sipelega'latl.html", "headword": "sipelega'latl", "example_index": 0, "raw_html_path": "raw/entries/8a3e117a58af7d4d2302c918c57db190e90e40cb497bedf2faa5b367be058976.html", "raw_html_sha256": "4738de9cfcede92044a0a6ef3f63154b40cb7447d3a395d07cb0e83db5907386", "fetched_at": "2026-07-12T02:45:04.464Z", "recordings": [ { "recording_id": "fdaeed5f2e3256951254e5b6a1c63503d8a9c276188f048bae31774cc911e60d", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/68d/68d66db0e817b112393ad327a145b735853a16bd2c39f49cd26a8036e2fe1033.mp3", "archive_relative_path": "raw/audio/68d/68d66db0e817b112393ad327a145b735853a16bd2c39f49cd26a8036e2fe1033.mp3" } ] } ], "prediction": "Malia'n gesatg ugta'latl ugtaqanigtug.", "reference": "Mali'an sipelega'latl ugwesgitji'jml ugjit jaqalipiasinin." }, { "id": "mic-sent-6234d6f27ee4d5cc13f72a47:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "One of my female friends lives in Metepna'qiaq.", "output_text": "Newte'jit nitape'sgw wigit Metepena'giaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "One of my female friends lives in Metepna'qiaq.", "mic_Latn": "Newte'jit nitape'sgw wigit Metepena'giaq." }, "canonical_ref": "entries/m/Metepna'qiaq/Metepna'qiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a40e2fe2b578d3de0992", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/Metepna'qiaq/Metepna'qiaq.html", "entry_url": "https://mikmaqonline.org/entries/m/Metepna'qiaq/Metepna'qiaq.html", "headword": "Metepna'qiaq", "example_index": 0, "raw_html_path": "raw/entries/c470d2835aad1d6542461983afba0a0a5bea5c52cba69190302bd30690a1f880.html", "raw_html_sha256": "bd05a348296f2d715901180962d1a1479026e7affbad3ece5c65ddfe3e5d3123", "fetched_at": "2026-07-12T02:41:25.689Z", "recordings": [ { "recording_id": "f7c806b4edca1cdc718bc3e267cb38e840d0be5a24819bd0171e7ddba2fb1852", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b53/b532dad5ee155da691f6ea6b72c221bf91dfab625d0cef7b4706824f0c6a8228.mp3", "archive_relative_path": "raw/audio/b53/b532dad5ee155da691f6ea6b72c221bf91dfab625d0cef7b4706824f0c6a8228.mp3" } ] } ], "prediction": "Newte'l nitap na Metepna'qiaq.", "reference": "Newte'jit nitape'sgw wigit Metepena'giaq." }, { "id": "mic-sent-629239d3bfa42ba8d9df937b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I've got five good boards.", "output_text": "Na'nijig gelu'sijig lasqo'plaq geggungig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I've got five good boards.", "mic_Latn": "Na'nijig gelu'sijig lasqo'plaq geggungig." }, "canonical_ref": "entries/n/na'nijig/na'nijig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-af7a332cf22047e69f41", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/na'nijig/na'nijig.html", "entry_url": "https://mikmaqonline.org/entries/n/na'nijig/na'nijig.html", "headword": "na'nijig", "example_index": 0, "raw_html_path": "raw/entries/e4885e973df8e082a66bb1ecc5e5a1b648bbac4bc50eac85333752e1ac2ae387.html", "raw_html_sha256": "4a9fd3c5c603925853a597773036c56d1f5d7031ad442becfde77699a796c112", "fetched_at": "2026-07-12T02:41:59.089Z", "recordings": [ { "recording_id": "62f9cdced780db22c17570c43255a404f8d6012895d771869509eb12da69eda0", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/244/24472e9ae22da2df47c94a1bdba014bb59090d47417820061a9729ebef076347.mp3", "archive_relative_path": "raw/audio/244/24472e9ae22da2df47c94a1bdba014bb59090d47417820061a9729ebef076347.mp3" } ] } ], "prediction": "Gi's gi's gaqapijig.", "reference": "Na'nijig gelu'sijig lasqo'plaq geggungig." }, { "id": "mic-sent-6293e07bd9528bc53394bd59:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I laugh every time I remember how silly that relative of mine can be.", "output_text": "Wesgewei te's migwite'tm ta'n teliamassij na no'gmaw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I laugh every time I remember how silly that relative of mine can be.", "mic_Latn": "Wesgewei te's migwite'tm ta'n teliamassij na no'gmaw." }, "canonical_ref": "entries/w/wesgewe'g/wesgewe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f651653ac50b1159fdcb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wesgewe'g/wesgewe'g.html", "entry_url": "https://mikmaqonline.org/entries/w/wesgewe'g/wesgewe'g.html", "headword": "wesgewe'g", "example_index": 0, "raw_html_path": "raw/entries/c6cde84f21250cc2fec40ae29a0ffd14616d2434f44f1798a2b4316020cf94d1.html", "raw_html_sha256": "39a8c4fe732a540ad438096cb16cec14d9e13d56ac861de16efb9c72770d6f34", "fetched_at": "2026-07-12T02:47:16.534Z", "recordings": [ { "recording_id": "b5485d76547cc04d810a7713f2243eae6b437ad9e95b21150e6f2e793b96be25", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6ba/6ba00f65e8d3ad82181600c01ce3a4cce5ec0f8d24a00ae1bf3ba961c8eb827f.mp3", "archive_relative_path": "raw/audio/6ba/6ba00f65e8d3ad82181600c01ce3a4cce5ec0f8d24a00ae1bf3ba961c8eb827f.mp3" } ] } ], "prediction": "Te's te's nige' ta'n tujiw ge's'g na ni'n te'sijig.", "reference": "Wesgewei te's migwite'tm ta'n teliamassij na no'gmaw." }, { "id": "mic-sent-633764bc7b5b834b44cf846c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Bring me five bottles.", "output_text": "Nanoqsijig pu'taig jugwa'tui.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Bring me five bottles.", "mic_Latn": "Nanoqsijig pu'taig jugwa'tui." }, "canonical_ref": "entries/n/nanoqsijig/nanoqsijig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-169a585d1dbf5ad901d2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nanoqsijig/nanoqsijig.html", "entry_url": "https://mikmaqonline.org/entries/n/nanoqsijig/nanoqsijig.html", "headword": "nanoqsijig", "example_index": 0, "raw_html_path": "raw/entries/62586a41c593004cf501747d35e9aae67576f846faf189be28fc9e14abb5d85c.html", "raw_html_sha256": "43bb73a8ae8d973938ecfb5a251bfbe3f817469bc8790f8519389c46e718933c", "fetched_at": "2026-07-12T02:41:59.796Z", "recordings": [ { "recording_id": "b3a07120192ea104d2894f3e685c7ee79d75f93b9d427fcfb8c3e10902d071dd", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a74/a7400474d9d06486a22b696effe84fcf7e40aa0bcd3bcb96f726ee2a92365e97.mp3", "archive_relative_path": "raw/audio/a74/a7400474d9d06486a22b696effe84fcf7e40aa0bcd3bcb96f726ee2a92365e97.mp3" } ] } ], "prediction": "Ge' jugwa's'g ta'n tujiw pilei.", "reference": "Nanoqsijig pu'taig jugwa'tui." }, { "id": "mic-sent-6374a28003838c88ee308c0a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she wants to shoot it, but is awkward with a gun.", "output_text": "Getu' pe'sg'g, pas'g awano'tg pe'sgewei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she wants to shoot it, but is awkward with a gun.", "mic_Latn": "Getu' pe'sg'g, pas'g awano'tg pe'sgewei." }, "canonical_ref": "entries/p/pe'sg'g/pe'sg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6a724ecef4145c91f891", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pe'sg'g/pe'sg'g.html", "entry_url": "https://mikmaqonline.org/entries/p/pe'sg'g/pe'sg'g.html", "headword": "pe'sg'g", "example_index": 0, "raw_html_path": "raw/entries/2bf01c6cfcefa36ee06c27c2c27e843a5ae3476351fcaf04a257a8f4f88a0e88.html", "raw_html_sha256": "7c3ffe0371936753aef65651dbface58a79148358ce0d55077d96f9284c8c541", "fetched_at": "2026-07-12T02:43:41.553Z", "recordings": [ { "recording_id": "d19ef6c6fc143301bba48a1693bc5e71808045b12e4ceeaf11b0ee23885afe60", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e97/e977f641d9247c9801166d6e878ee88388cbb6fa7b352ffa7f2146b8f90942c3.mp3", "archive_relative_path": "raw/audio/e97/e977f641d9247c9801166d6e878ee88388cbb6fa7b352ffa7f2146b8f90942c3.mp3" } ] } ], "prediction": "Ge's gesatgwalatl, gatu gesatg.", "reference": "Getu' pe'sg'g, pas'g awano'tg pe'sgewei." }, { "id": "mic-sent-63791cfd2e89ed6e3b8f554b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When he/she sent off his/her child he/she provided plenty of food for him/her to bring along.", "output_text": "Poqtigimateg unjann gaqatepiaqap mijipjewei ignmuaj nespnmnin.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When he/she sent off his/her child he/she provided plenty of food for him/her to bring along.", "mic_Latn": "Poqtigimateg unjann gaqatepiaqap mijipjewei ignmuaj nespnmnin." }, "canonical_ref": "entries/p/poqtigimatl/poqtigimatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-41ac0d75ac55e3e189de", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/poqtigimatl/poqtigimatl.html", "entry_url": "https://mikmaqonline.org/entries/p/poqtigimatl/poqtigimatl.html", "headword": "poqtigimatl", "example_index": 0, "raw_html_path": "raw/entries/2b0738670a2b223f0681c3e8520392fe6bf3384f16e7dc129d498ca6646b68db.html", "raw_html_sha256": "f68315d56f4726dd43aebf177dc195437337c81e9f6f00ae2770ddc22f7b6f00", "fetched_at": "2026-07-12T02:44:16.832Z", "recordings": [ { "recording_id": "01f8be3957591e02df682523d8ab80273a6da6e0a58df4178217c48961271324", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c03/c030f126b064448377c8778b53cf707dd58db099b416d3a54eb5f701d624dd2c.mp3", "archive_relative_path": "raw/audio/c03/c030f126b064448377c8778b53cf707dd58db099b416d3a54eb5f701d624dd2c.mp3" } ] } ], "prediction": "Ta'n tujiw gesatg ugjit ugjit lpa gmu'j.", "reference": "Poqtigimateg unjann gaqatepiaqap mijipjewei ignmuaj nespnmnin." }, { "id": "mic-sent-63aa5ab7ddbfeed2fa01ad43:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I am not envious about the coronor's job.", "output_text": "Mu ni'n wisgualaq ta'n nutapteget telugwej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I am not envious about the coronor's job.", "mic_Latn": "Mu ni'n wisgualaq ta'n nutapteget telugwej." }, "canonical_ref": "entries/n/nutapteget/nutapteget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-336701f503b2e3935b8e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nutapteget/nutapteget.html", "entry_url": "https://mikmaqonline.org/entries/n/nutapteget/nutapteget.html", "headword": "nutapteget", "example_index": 0, "raw_html_path": "raw/entries/a3424d7f5612cd890679c3a9ebca1193c29ceb5b601ca3a569e6b6b07f015ef9.html", "raw_html_sha256": "178a34c8e2b9a6f71911ab6d5b949a921078cb05329dda615598f5826e158aca", "fetched_at": "2026-07-12T02:42:55.327Z", "recordings": [ { "recording_id": "a7b4d2dd5040fb887f8bcfa2a6551bcf19f728f973e4de85fb4898edea7c5e3e", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4c2/4c2299abddee53aaa64689c07dbfd8fc7ec0136aab39b126b5af706ad9ff0236.mp3", "archive_relative_path": "raw/audio/4c2/4c2299abddee53aaa64689c07dbfd8fc7ec0136aab39b126b5af706ad9ff0236.mp3" } ] } ], "prediction": "Mu ni'n gesatg ta'n te'sipowji'jg.", "reference": "Mu ni'n wisgualaq ta'n nutapteget telugwej." }, { "id": "mic-sent-63bf53c86b7ad489d47070d3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I'm going to run up the mission.", "output_text": "Pe' wanne'g eli'piap.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I'm going to run up the mission.", "mic_Latn": "Pe' wanne'g eli'piap." }, "canonical_ref": "entries/w/wanne'g/wanne'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-66cd5ad2426e1387767c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wanne'g/wanne'g.html", "entry_url": "https://mikmaqonline.org/entries/w/wanne'g/wanne'g.html", "headword": "wanne'g", "example_index": 0, "raw_html_path": "raw/entries/b29adcc10c82a6affa01670298e1cafb37f98cd50a2e03c2d3050415ee653720.html", "raw_html_sha256": "b9ee5fa8d55c6bc95f764b086ef828ea0cb5daa04b2448cb3129aef4fd675010", "fetched_at": "2026-07-12T02:46:31.383Z", "recordings": [ { "recording_id": "6f54fa892d728f4ec1cfab28a7ef46039b72433119e2d865d7fb6ae2322a549b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/be9/be9ce6561e89efa6eda27bbd8342a97088c352b5ed5439d6aa28efae4b82a496.mp3", "archive_relative_path": "raw/audio/be9/be9ce6561e89efa6eda27bbd8342a97088c352b5ed5439d6aa28efae4b82a496.mp3" } ] } ], "prediction": "Ni'n goqwei lugowaqan.", "reference": "Pe' wanne'g eli'piap." }, { "id": "mic-sent-64eca0bb5f0c01a1f0a563d5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Peter likes using \"certainly\".", "output_text": "Pie'l na mawigsatg e'w'g \"getletug\".", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Peter likes using \"certainly\".", "mic_Latn": "Pie'l na mawigsatg e'w'g \"getletug\"." }, "canonical_ref": "entries/g/getletug/getletug.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-be8fe871326d61139950", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/getletug/getletug.html", "entry_url": "https://mikmaqonline.org/entries/g/getletug/getletug.html", "headword": "getletug", "example_index": 0, "raw_html_path": "raw/entries/5ee80b3d84685df73d64cdfc0c2986765634c99de57d377c5e0995b4c14002e1.html", "raw_html_sha256": "53ff592316ef2cc93fba8bc6d477fe1818e3457ca77089c5a1347fd055ad99d6", "fetched_at": "2026-07-12T02:39:23.191Z", "recordings": [ { "recording_id": "7d1a84b3f9b48a2b34f38a198522f0e85ce59055086ba7bc92f0dc2d772983eb", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/987/9873af762a21ed64fbf272aab6fa3e751d73537ad46d141c32177bd3fd802395.mp3", "archive_relative_path": "raw/audio/987/9873af762a21ed64fbf272aab6fa3e751d73537ad46d141c32177bd3fd802395.mp3" } ] } ], "prediction": "Pie'l gesatg ugjit \"s'te'l\".", "reference": "Pie'l na mawigsatg e'w'g \"getletug\"." }, { "id": "mic-sent-6510d33f40ef6abf04b39a85:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A mariner travels all over the world.", "output_text": "Alaqtegewinu gaqpeigwa'sit ugs'tqamug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A mariner travels all over the world.", "mic_Latn": "Alaqtegewinu gaqpeigwa'sit ugs'tqamug." }, "canonical_ref": "entries/a/alaqtegewinu/alaqtegewinu.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0e37f2093d2cd835a896", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/alaqtegewinu/alaqtegewinu.html", "entry_url": "https://mikmaqonline.org/entries/a/alaqtegewinu/alaqtegewinu.html", "headword": "alaqtegewinu", "example_index": 0, "raw_html_path": "raw/entries/6d57a5a9fecd426dc4072208b12eb542196a26eaddb545535761a7c17bf2d2c9.html", "raw_html_sha256": "c6c67c1d7428d46cbd733822a3749ff48d3a0fcf79fa2663a9dc9cbebae7fe76", "fetched_at": "2026-07-12T02:36:37.717Z", "recordings": [ { "recording_id": "f18a88217db3efb5ed52b2c9754adb53f770b48700e184cfdb2db0368c104fd8", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/872/87281b4e298adcfbe6f7d9510a0f47e69425981677d46439200dbd2a601f8958.mp3", "archive_relative_path": "raw/audio/872/87281b4e298adcfbe6f7d9510a0f47e69425981677d46439200dbd2a601f8958.mp3" } ] } ], "prediction": "Pugwelg na te's'g ta'n te'sipu'g.", "reference": "Alaqtegewinu gaqpeigwa'sit ugs'tqamug." }, { "id": "mic-sent-65e4074a0d381d26f3003fb4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What time will you (plural exclusive) be going to fish for salmon?", "output_text": "Ta's ajietew najiplamugutioq?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What time will you (plural exclusive) be going to fish for salmon?", "mic_Latn": "Ta's ajietew najiplamugutioq?" }, "canonical_ref": "entries/p/plamugwet/plamugwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-94de150784d4e5438b60", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/plamugwet/plamugwet.html", "entry_url": "https://mikmaqonline.org/entries/p/plamugwet/plamugwet.html", "headword": "plamugwet", "example_index": 0, "raw_html_path": "raw/entries/2192d756160a502e83017df1023a692dcc93c3ebe8827699fe0ffb9dbaa0ef6c.html", "raw_html_sha256": "e99c1e234c297da2c5404e3a1b630ade76a70dc181c72c385ab71450ce40bd60", "fetched_at": "2026-07-12T02:44:11.702Z", "recordings": [ { "recording_id": "7583fdeb1892e83881fe525c24124d1edcad2939418666a170a0de44904920ea", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/888/888812cef3472c159806532a649318cf4b0289cb9a67056271f85f3c866a260b.mp3", "archive_relative_path": "raw/audio/888/888812cef3472c159806532a649318cf4b0289cb9a67056271f85f3c866a260b.mp3" } ] } ], "prediction": "Ta's'g ta'n tujiw plamu'g?", "reference": "Ta's ajietew najiplamugutioq?" }, { "id": "mic-sent-6790456bd4c25b27956038f8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Let me fry that fish.", "output_text": "Ge' ni'n sisla'gwa'lg'p na nme'j.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Let me fry that fish.", "mic_Latn": "Ge' ni'n sisla'gwa'lg'p na nme'j." }, "canonical_ref": "entries/s/sisla'gwa'latl/sisla'gwa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-fa0f58e1be7594edabab", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sisla'gwa'latl/sisla'gwa'latl.html", "entry_url": "https://mikmaqonline.org/entries/s/sisla'gwa'latl/sisla'gwa'latl.html", "headword": "sisla'gwa'latl", "example_index": 0, "raw_html_path": "raw/entries/302c0cb05242c31844b4e5be405807466540cb12b1a4db0ac2574744033dd28e.html", "raw_html_sha256": "691b0534dee7f8cef5b1a6b458f8580174db841428237e4dd6d12d0c2499ec73", "fetched_at": "2026-07-12T02:45:08.081Z", "recordings": [ { "recording_id": "d3fbaddf87b037ffbe8e3ef12eb0bacd16684a750da37778c8b30484fecc20f2", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/da8/da832f2523aa51e8075c4b047ac488555f5bf373e7e51cf6e772f595e8f3a209.mp3", "archive_relative_path": "raw/audio/da8/da832f2523aa51e8075c4b047ac488555f5bf373e7e51cf6e772f595e8f3a209.mp3" } ] } ], "prediction": "Ge' lpa nmu'j na nuji'j.", "reference": "Ge' ni'n sisla'gwa'lg'p na nme'j." }, { "id": "mic-sent-67f4a88ee86a0e7e17273220:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I have fifty books.", "output_text": "Nanisga'qal te's'gl eggunmann wi'gatignn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I have fifty books.", "mic_Latn": "Nanisga'qal te's'gl eggunmann wi'gatignn." }, "canonical_ref": "entries/n/nanisga'qal/nanisga'qal.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f879a4d6389e0e2f1e8d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nanisga'qal/nanisga'qal.html", "entry_url": "https://mikmaqonline.org/entries/n/nanisga'qal/nanisga'qal.html", "headword": "nanisga'qal", "example_index": 0, "raw_html_path": "raw/entries/427dba3b4023d27e18998bdedfc4d42ad35cdf0c0a05aa70e1b897cded32d24b.html", "raw_html_sha256": "94c4fa0ec56ee8d74f129e569941f71f6d5ef014742a4b9d5eac5e3cff09a050", "fetched_at": "2026-07-12T02:41:59.391Z", "recordings": [ { "recording_id": "251e3e09880eef05d56e248cc3d9419df1833d8adecdecc0663f09d248a332db", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0f5/0f5487dbf9b8e08d2c1a69146444b84568e8d4f4e3f2f847d124e8c3c2ede03b.mp3", "archive_relative_path": "raw/audio/0f5/0f5487dbf9b8e08d2c1a69146444b84568e8d4f4e3f2f847d124e8c3c2ede03b.mp3" } ] } ], "prediction": "Gi's nige' pisgi'g wi'gatign.", "reference": "Nanisga'qal te's'gl eggunmann wi'gatignn." }, { "id": "mic-sent-68a9cefd74db7aa746ca6434:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Don't bring that lazy one where I'm working.", "output_text": "Mut jugwa'lanew na malo'pj ta'n etllugwei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Don't bring that lazy one where I'm working.", "mic_Latn": "Mut jugwa'lanew na malo'pj ta'n etllugwei." }, "canonical_ref": "entries/m/malo'pj/malo'pj.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-932327a8408e111318f5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/malo'pj/malo'pj.html", "entry_url": "https://mikmaqonline.org/entries/m/malo'pj/malo'pj.html", "headword": "malo'pj", "example_index": 0, "raw_html_path": "raw/entries/ce2328991cb547a6a26f8ba042edbf4d8b9a312cbcd4666a8e675a56a53a9ba7.html", "raw_html_sha256": "45221246c7936193a0de76dba8cd0db5cf7584bc325dd864ca9068f6d02890f0", "fetched_at": "2026-07-12T02:40:45.322Z", "recordings": [ { "recording_id": "253086acef7f3b7754580ec8f38b1429d7aafd6252b45d4e9963ca2d8f7e4a1c", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b73/b73a707722530bce06edfe9840536b9ef71bf4f8e217ce8a6d039b1efcf0d1a4.mp3", "archive_relative_path": "raw/audio/b73/b73a707722530bce06edfe9840536b9ef71bf4f8e217ce8a6d039b1efcf0d1a4.mp3" } ] } ], "prediction": "Mut telia'tu na lugowa'q ta'n tujiw etlugowaqan.", "reference": "Mut jugwa'lanew na malo'pj ta'n etllugwei." }, { "id": "mic-sent-68c8e1ab9f77016698210d96:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The woman has her child with her.", "output_text": "E'pit ala'latl unjann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The woman has her child with her.", "mic_Latn": "E'pit ala'latl unjann." }, "canonical_ref": "entries/a/ala'latl/ala'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-99e4f9345e2e20688a96", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/ala'latl/ala'latl.html", "entry_url": "https://mikmaqonline.org/entries/a/ala'latl/ala'latl.html", "headword": "ala'latl", "example_index": 0, "raw_html_path": "raw/entries/72c469008bdd6979b07f379e8342a9a39b6e7551f2fd9a3a3aa0906e9b10f101.html", "raw_html_sha256": "4861d1d962831e093587f8b02534c0eff5e947db27d64ca1ff96f6d940a5922f", "fetched_at": "2026-07-12T02:36:33.988Z", "recordings": [ { "recording_id": "3525516fed845e855e42ea6b7bc1ffaa7ec8571b0cfc1f7bbe269c464e87333d", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/97a/97a61cc3db4c04800f327517ca74f69a744709b406fae7bdb2c301947c7e6ccb.mp3", "archive_relative_path": "raw/audio/97a/97a61cc3db4c04800f327517ca74f69a744709b406fae7bdb2c301947c7e6ccb.mp3" } ] } ], "prediction": "E'pite'ji'j ugjit.", "reference": "E'pit ala'latl unjann." }, { "id": "mic-sent-69387c7db9b619b420db4766:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she teaches his/her child how to speak Mi'gmaq (an aboriginal language).", "output_text": "Gegina'muatl unjann ta'n telinnui'simg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she teaches his/her child how to speak Mi'gmaq (an aboriginal language).", "mic_Latn": "Gegina'muatl unjann ta'n telinnui'simg." }, "canonical_ref": "entries/g/gegina'muatl/gegina'muatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-98f4a53d4acd53916690", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gegina'muatl/gegina'muatl.html", "entry_url": "https://mikmaqonline.org/entries/g/gegina'muatl/gegina'muatl.html", "headword": "gegina'muatl", "example_index": 0, "raw_html_path": "raw/entries/18914e481a4016a2758547252f6ad568530feef12520d8dac9b14fdf39c6c9a0.html", "raw_html_sha256": "ce93f355ab26365e9cbb6c1b02059446347af9f6ccb606745ba7cd7ad7cd23a8", "fetched_at": "2026-07-12T02:38:48.637Z", "recordings": [ { "recording_id": "c2cbb417af8a088f7851d2985c413cc8080569924ff74cd9344562a61207a119", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f09/f09c7aa4ea1e276980e698aeb0868dbe4ab63ddbdae76fd2ac6c13346ebb701e.mp3", "archive_relative_path": "raw/audio/f09/f09c7aa4ea1e276980e698aeb0868dbe4ab63ddbdae76fd2ac6c13346ebb701e.mp3" } ] } ], "prediction": "Mi'gme'g ugjit ugjigtug.", "reference": "Gegina'muatl unjann ta'n telinnui'simg." }, { "id": "mic-sent-6b173af875df2bb329e0b552:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she fell off the house and he/she didn't get hurt.", "output_text": "Wenji'guomg wejnisiet aq mu jileiug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she fell off the house and he/she didn't get hurt.", "mic_Latn": "Wenji'guomg wejnisiet aq mu jileiug." }, "canonical_ref": "entries/n/nisiet/nisiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-20ee2879bc1bdb7f8b78", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nisiet/nisiet.html", "entry_url": "https://mikmaqonline.org/entries/n/nisiet/nisiet.html", "headword": "nisiet", "example_index": 0, "raw_html_path": "raw/entries/83be43d5a03498b1616a2df4f8124e7f4db525868a3269e757ff78a2df19ddcb.html", "raw_html_sha256": "f3d0dc695dd44c2d3cca46f9b761fed4e052adcc704b16cda4240bbb21f7ebe9", "fetched_at": "2026-07-12T02:42:37.238Z", "recordings": [ { "recording_id": "6ebc8d689a33e59305ad035b0864ef1b6546d6ee1edc91026b377d7d1b13c7e9", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ae1/ae11b22a0c7b2e0ce3d50ee8a0b0e8b00c4c7faf2328a5657e8429a8ff5c7c50.mp3", "archive_relative_path": "raw/audio/ae1/ae11b22a0c7b2e0ce3d50ee8a0b0e8b00c4c7faf2328a5657e8429a8ff5c7c50.mp3" } ] } ], "prediction": "Gi's gesatg aq mu gesigwet.", "reference": "Wenji'guomg wejnisiet aq mu jileiug." }, { "id": "mic-sent-6b1c246c3bf34dd8ebddac35:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's hard to find a long straight boat pole.", "output_text": "Metua'sit gi'gamgo'n ta'n pegoqsit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's hard to find a long straight boat pole.", "mic_Latn": "Metua'sit gi'gamgo'n ta'n pegoqsit." }, "canonical_ref": "entries/g/gi'gamgo'n/gi'gamgo'n.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-72c6f2129c0c304d7eb4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gi'gamgo'n/gi'gamgo'n.html", "entry_url": "https://mikmaqonline.org/entries/g/gi'gamgo'n/gi'gamgo'n.html", "headword": "gi'gamgo'n", "example_index": 0, "raw_html_path": "raw/entries/d6c9f6d03ab1ed90ec2d6259250697065fc193234a50c3a61ea3b4e53243eeb8.html", "raw_html_sha256": "cc65ac1f19cc070d7d05bf9e5bce5bc78d1c020b0595e468c00448b3fe188366", "fetched_at": "2026-07-12T02:39:29.113Z", "recordings": [ { "recording_id": "69ce01359cb3401583862b5699497ed1bb588390dc529c48dd3a160a32198103", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bb7/bb791dbc59900f8b12ded97728dc9fe4c43d00f190d5eed1eadc2e97a00d8265.mp3", "archive_relative_path": "raw/audio/bb7/bb791dbc59900f8b12ded97728dc9fe4c43d00f190d5eed1eadc2e97a00d8265.mp3" } ] } ], "prediction": "We'gwi'g goqwei ta'n tujiw gmu'j.", "reference": "Metua'sit gi'gamgo'n ta'n pegoqsit." }, { "id": "mic-sent-6ba3a90c7aa2d3129586d005:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she lends him/her a shirt.", "output_text": "Emqatu'atl atlail.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she lends him/her a shirt.", "mic_Latn": "Emqatu'atl atlail." }, "canonical_ref": "entries/e/emqatu'atl/emqatu'atl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-42832f741b00851522bd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/emqatu'atl/emqatu'atl.html", "entry_url": "https://mikmaqonline.org/entries/e/emqatu'atl/emqatu'atl.html", "headword": "emqatu'atl", "example_index": 0, "raw_html_path": "raw/entries/16ccdb647b49c2568074d770240e92bbfe5e6a6d9ca366472625df724fca8529.html", "raw_html_sha256": "fc4c3b65b302cfd1f900862dff4aabac5f5c09a5ef438876e80356bcf5fb341b", "fetched_at": "2026-07-12T02:37:58.568Z", "recordings": [ { "recording_id": "84b99e41730d7908a04c336b9ea6c816de4bcaeff63cc2f3cccc581046ec0a14", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/52f/52f9a2d8e08653865777f08a6678df82917b4957c3760596591d17f11ae3d2fe.mp3", "archive_relative_path": "raw/audio/52f/52f9a2d8e08653865777f08a6678df82917b4957c3760596591d17f11ae3d2fe.mp3" } ] } ], "prediction": "Amujpa'latl ugjitl.", "reference": "Emqatu'atl atlail." }, { "id": "mic-sent-6bf7f8cc78bac1aef804deec:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "They gather and stand together and ask for more work.", "output_text": "Mawpugueta'jig aq gelutmi'tij me' pugwelg lugowaqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "They gather and stand together and ask for more work.", "mic_Latn": "Mawpugueta'jig aq gelutmi'tij me' pugwelg lugowaqan." }, "canonical_ref": "entries/m/mawpugueta'jig/mawpugueta'jig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5bc7cacae9f2824fb8eb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mawpugueta'jig/mawpugueta'jig.html", "entry_url": "https://mikmaqonline.org/entries/m/mawpugueta'jig/mawpugueta'jig.html", "headword": "mawpugueta'jig", "example_index": 0, "raw_html_path": "raw/entries/303503f45522ccd132ee4dfb11a31a415ad2a698156545f496aaa890cfa3ce2f.html", "raw_html_sha256": "daf944b1fd9cc82ff14b9d89cad85f1c49bf100b249be78e45e0450550f3463c", "fetched_at": "2026-07-12T02:41:03.528Z", "recordings": [ { "recording_id": "cb458659dc48d357e6979563603e2dd6d2c3e25e09364921398d2b60bff97e95", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1db/1dba4fbd8cc6ad5c059b5bafd1efd0f631e2fc52a0e56dd5634e5dc7edeeed1e.mp3", "archive_relative_path": "raw/audio/1db/1dba4fbd8cc6ad5c059b5bafd1efd0f631e2fc52a0e56dd5634e5dc7edeeed1e.mp3" } ] } ], "prediction": "Amujpa'tu'n aq mesga'toq aq mesgi'gig ta'n tujiw.", "reference": "Mawpugueta'jig aq gelutmi'tij me' pugwelg lugowaqan." }, { "id": "mic-sent-6c4e0a6e00aa16ff462da8c7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "We are going bird hunting tomorrow.", "output_text": "Sisipewe'ga'tieg sapo'nug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "We are going bird hunting tomorrow.", "mic_Latn": "Sisipewe'ga'tieg sapo'nug." }, "canonical_ref": "entries/s/sisipewe'get/sisipewe'get.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-489b3a9a77ee5d44ed21", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sisipewe'get/sisipewe'get.html", "entry_url": "https://mikmaqonline.org/entries/s/sisipewe'get/sisipewe'get.html", "headword": "sisipewe'get", "example_index": 0, "raw_html_path": "raw/entries/d62c45e24414e2c28bbec4479e8ce96e368af432f6f92127e9ab7f368b95c4e5.html", "raw_html_sha256": "550fe45d2a8834d55dd401e7abf3d20881aa75d232f000985e73b2320417328f", "fetched_at": "2026-07-12T02:36:14.372Z", "recordings": [ { "recording_id": "df88b307f7d0126487507889becac0b832fab267d87cdb51c90d06a9a2f2390f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/02b/02b466b8d564aa3bc57d6ccb264c30e103930e58d463527ecffd58fd11915b7b.mp3", "archive_relative_path": "raw/audio/02b/02b466b8d564aa3bc57d6ccb264c30e103930e58d463527ecffd58fd11915b7b.mp3" } ] } ], "prediction": "Sapo'gwe'g gisgug.", "reference": "Sisipewe'ga'tieg sapo'nug." }, { "id": "mic-sent-6c8029ab2f08af79d8bd5968:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she locks the door on Jean-Batiste.", "output_text": "Apt'sqa'muatl Sapatisal.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she locks the door on Jean-Batiste.", "mic_Latn": "Apt'sqa'muatl Sapatisal." }, "canonical_ref": "entries/a/apt'sqa'muatl/apt'sqa'muatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2ba9fcd6fe11f5afcf27", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/apt'sqa'muatl/apt'sqa'muatl.html", "entry_url": "https://mikmaqonline.org/entries/a/apt'sqa'muatl/apt'sqa'muatl.html", "headword": "apt'sqa'muatl", "example_index": 0, "raw_html_path": "raw/entries/3b7971e1b637758083632348dd2e99f43fceb55b1324aff7065fbb72befa61c0.html", "raw_html_sha256": "1ea22107cda2ec61c1cb184c30c547ae96cce23548eb4a714a96913acc413b06", "fetched_at": "2026-07-12T02:37:13.043Z", "recordings": [ { "recording_id": "2dd7e5756c796e3c1ef1423dcfc73d02fcc019f37c8f6b776334012ca636d04e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f94/f94813effbdf61d00fd8e8fa12a2128ac3ba5dfcf2482794f2d7edc62b1c2a69.mp3", "archive_relative_path": "raw/audio/f94/f94813effbdf61d00fd8e8fa12a2128ac3ba5dfcf2482794f2d7edc62b1c2a69.mp3" } ] } ], "prediction": "Je'n-Batiste'l gaqapi'latl.", "reference": "Apt'sqa'muatl Sapatisal." }, { "id": "mic-sent-6df51fba21e46a5443754410:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who is that turning at the road?", "output_text": "Wentanet etlgawasga'sit awtigtug?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who is that turning at the road?", "mic_Latn": "Wentanet etlgawasga'sit awtigtug?" }, "canonical_ref": "entries/g/gawasga'sit/gawasga'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e9ba54d6acec98c3e050", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gawasga'sit/gawasga'sit.html", "entry_url": "https://mikmaqonline.org/entries/g/gawasga'sit/gawasga'sit.html", "headword": "gawasga'sit", "example_index": 0, "raw_html_path": "raw/entries/9e4346ebe3f448e2ed06e06880794b6e52d3e6920ad626617bb33bc8ce226d60.html", "raw_html_sha256": "3f34cc3e8851f5ab83acd2e993adc091b96555753a161c829b66d7b9f600b0fd", "fetched_at": "2026-07-12T02:38:46.020Z", "recordings": [ { "recording_id": "d18ff59d3cddb78d5e7920744ed11fbd4c54f2eee753bba0469744b7ad2c8079", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/19b/19b46ee581577ca0fcdc9be32612f85375670f094b71bd4a487c7ca5348f9191.mp3", "archive_relative_path": "raw/audio/19b/19b46ee581577ca0fcdc9be32612f85375670f094b71bd4a487c7ca5348f9191.mp3" } ] } ], "prediction": "Wen e'pit na ula lpaqanigtug?", "reference": "Wentanet etlgawasga'sit awtigtug?" }, { "id": "mic-sent-6dfb5ee3eac99e82d8a2c737:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The old man slips and falls on the floor.", "output_text": "Gisigu saqatuetesing msaqtaqtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The old man slips and falls on the floor.", "mic_Latn": "Gisigu saqatuetesing msaqtaqtug." }, "canonical_ref": "entries/s/saqatuetesing/saqatuetesing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6f13d1606d38a83af032", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/saqatuetesing/saqatuetesing.html", "entry_url": "https://mikmaqonline.org/entries/s/saqatuetesing/saqatuetesing.html", "headword": "saqatuetesing", "example_index": 0, "raw_html_path": "raw/entries/7530334203976870ff39bc67a95b0ab4ac9e543f1ebc20e362bf278ea24fbd43.html", "raw_html_sha256": "5b4acb8c5c78370a49eaf6ccc1f07add52da383d514a11d45da80cf35065b5b6", "fetched_at": "2026-07-12T02:44:42.442Z", "recordings": [ { "recording_id": "94cb06ce3f5d0181e4cb29edd2841ef2a9b821c7ab5d9207821aa2042c3c31dc", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6b1/6b149896b1711c31b1904826eb15e2bf5c5296f7e7f1aa6a07580246d5ecb5d2.mp3", "archive_relative_path": "raw/audio/6b1/6b149896b1711c31b1904826eb15e2bf5c5296f7e7f1aa6a07580246d5ecb5d2.mp3" } ] } ], "prediction": "Gisigu's'g aq gesatg.", "reference": "Gisigu saqatuetesing msaqtaqtug." }, { "id": "mic-sent-6e1de2333cba7fdfd6c2b634:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she saws the plank as if he/she knew what he/she was doing.", "output_text": "Lasqo'plawl tela'gipulatl s'tge' gji'toq ta'n telugwej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she saws the plank as if he/she knew what he/she was doing.", "mic_Latn": "Lasqo'plawl tela'gipulatl s'tge' gji'toq ta'n telugwej." }, "canonical_ref": "entries/t/tela'gipulatl/tela'gipulatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-48c6b822933dd5b1408c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tela'gipulatl/tela'gipulatl.html", "entry_url": "https://mikmaqonline.org/entries/t/tela'gipulatl/tela'gipulatl.html", "headword": "tela'gipulatl", "example_index": 0, "raw_html_path": "raw/entries/9df2fc9bbf525a0d4716aabea38f6caff13c008316b3a3302c1a9dce3a6ce2c2.html", "raw_html_sha256": "3d48051c7e9e4eee3217a07043d5a52dfde59ccfa16e86baab1d5ceac07c1f99", "fetched_at": "2026-07-12T02:45:29.170Z", "recordings": [ { "recording_id": "6a4192fd2c63f06c13d15de4b1508c8de4cb8e88567af113456d34fd42d6fa3c", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6ee/6eec69b61c28f97450d17a88091416b6edcfcd9011d6ad6d193b66d6d64ce88d.mp3", "archive_relative_path": "raw/audio/6ee/6eec69b61c28f97450d17a88091416b6edcfcd9011d6ad6d193b66d6d64ce88d.mp3" } ] } ], "prediction": "Gesga'latl lpa wi'gatl ta'n goqwei wejgu't.", "reference": "Lasqo'plawl tela'gipulatl s'tge' gji'toq ta'n telugwej." }, { "id": "mic-sent-6e60fc2a6e30a50f50fb4f2c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My sister is my grandchild's godmother.", "output_text": "Ngweji'j geggunawet ugit nuji'jl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My sister is my grandchild's godmother.", "mic_Latn": "Ngweji'j geggunawet ugit nuji'jl." }, "canonical_ref": "entries/g/geggunawet/geggunawet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a26c3032f4083c501d93", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/geggunawet/geggunawet.html", "entry_url": "https://mikmaqonline.org/entries/g/geggunawet/geggunawet.html", "headword": "geggunawet", "example_index": 0, "raw_html_path": "raw/entries/f51cd39ad357c3e7e606561febf087ef8e33cf161feb4e7acbad64f5543addaf.html", "raw_html_sha256": "647bec0dc36d15ec9929d404503161703bab76a75fff8e3b28d1bce2212fb7ee", "fetched_at": "2026-07-12T02:38:48.236Z", "recordings": [ { "recording_id": "e9b1223bfdecc0e7e3a61e764405b563908ebeb08613fb835b9d2cf4a7d66f6c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c3c/c3c0cd82bac43e1e626edcecff48f7bc9951a9141b2a350c409941638d7b206b.mp3", "archive_relative_path": "raw/audio/c3c/c3c0cd82bac43e1e626edcecff48f7bc9951a9141b2a350c409941638d7b206b.mp3" } ] } ], "prediction": "Ngwis na nuji'j na nugu'l.", "reference": "Ngweji'j geggunawet ugit nuji'jl." }, { "id": "mic-sent-6ebd1b20eb880eea29165768:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Your grandchild is cute.", "output_text": "Wigwasamugsit na guji'j.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Your grandchild is cute.", "mic_Latn": "Wigwasamugsit na guji'j." }, "canonical_ref": "entries/w/wigwasamugsit/wigwasamugsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-280689e26e3baacc1940", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wigwasamugsit/wigwasamugsit.html", "entry_url": "https://mikmaqonline.org/entries/w/wigwasamugsit/wigwasamugsit.html", "headword": "wigwasamugsit", "example_index": 0, "raw_html_path": "raw/entries/4cc5aa8523f66224499e62adadad6568c6ad136aeac1425e0e84076be31c5982.html", "raw_html_sha256": "e8f9f5979607e8216a47fde194cce80afd00e8e6fc901b7ac41e72cacdcf0120", "fetched_at": "2026-07-12T02:47:31.915Z", "recordings": [ { "recording_id": "844c160157d807f8df24d6c637097ef05821e42d5b654371c5b04950a6ef984d", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/012/0126982069cf693e75d438027429f47e5b28b41dcb32df2a64890d3a2dd1b2a5.mp3", "archive_relative_path": "raw/audio/012/0126982069cf693e75d438027429f47e5b28b41dcb32df2a64890d3a2dd1b2a5.mp3" } ] } ], "prediction": "Nuji'j na we'gwig.", "reference": "Wigwasamugsit na guji'j." }, { "id": "mic-sent-6ef6dbd8c406a0005d75b1f1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This card is damp, is the table wet?", "output_text": "Nenmue'g ula la'sgw, saqpe'g pata'uti?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This card is damp, is the table wet?", "mic_Latn": "Nenmue'g ula la'sgw, saqpe'g pata'uti?" }, "canonical_ref": "entries/n/nenmue'g/nenmue'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f1bf171e85952e336d1e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nenmue'g/nenmue'g.html", "entry_url": "https://mikmaqonline.org/entries/n/nenmue'g/nenmue'g.html", "headword": "nenmue'g", "example_index": 0, "raw_html_path": "raw/entries/b68f21699798feb36e1253e78cdd54151b7e707d1a22a9039e87c3c27ae89ef9.html", "raw_html_sha256": "93e7a2c07181cbc874538c1fdc3596c5651af8168f57fd3dc9584a9e1c87d593", "fetched_at": "2026-07-12T02:42:19.330Z", "recordings": [ { "recording_id": "101f41d91bc3b218c5e15bbf3daad26550e46f262d226b7a622b2d9a29e41d00", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f83/f83334820a3a0ab2cbb61381bfe823201dc6a342b53da6728c2266f16a02bf03.mp3", "archive_relative_path": "raw/audio/f83/f83334820a3a0ab2cbb61381bfe823201dc6a342b53da6728c2266f16a02bf03.mp3" } ] } ], "prediction": "We'gwi'g ula wi'gatign, amujpa we'gwatign?", "reference": "Nenmue'g ula la'sgw, saqpe'g pata'uti?" }, { "id": "mic-sent-6f056d4ecd9dd3b325690231:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Which rubbing compound shall I use?", "output_text": "Tegen a'megensuti e'w'tes?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Which rubbing compound shall I use?", "mic_Latn": "Tegen a'megensuti e'w'tes?" }, "canonical_ref": "entries/a/a'megensuti/a'megensuti.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3fb5506daf67dc1acf01", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/a'megensuti/a'megensuti.html", "entry_url": "https://mikmaqonline.org/entries/a/a'megensuti/a'megensuti.html", "headword": "a'megensuti", "example_index": 0, "raw_html_path": "raw/entries/94c6481a7f6cb7248a1f4b153fe11f67931cc9576a44e390680bf787d8546985.html", "raw_html_sha256": "b6532dc9620471ce1743e8c5f6d0088f76da433ae31a1cca762d87f22241abdf", "fetched_at": "2026-07-12T02:36:49.773Z", "recordings": [ { "recording_id": "5c94b0db1e3f864f3196de93ab0462496111b7f71f2d5f571b7f4a0ff0b946e0", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9ee/9ee129ce0ebb4e44819b29cc2de0b33add0ec08122d08d78e42cf28707f46df9.mp3", "archive_relative_path": "raw/audio/9ee/9ee129ce0ebb4e44819b29cc2de0b33add0ec08122d08d78e42cf28707f46df9.mp3" } ] } ], "prediction": "Ta'n te's'g ta'n tujiw eliei?", "reference": "Tegen a'megensuti e'w'tes?" }, { "id": "mic-sent-6f0e53c3cf7f42d82928cc02:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Be careful, don't go too close to the road, that vechicle coming in this direction is going so fast.", "output_text": "Ango'te'n, mut ugsam gigja'siw awti, teligsigawa's'g ala wejgwateja's'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Be careful, don't go too close to the road, that vechicle coming in this direction is going so fast.", "mic_Latn": "Ango'te'n, mut ugsam gigja'siw awti, teligsigawa's'g ala wejgwateja's'g." }, "canonical_ref": "entries/w/wejgwateja's'g/wejgwateja's'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-37d6a354b5734b8d0dcd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejgwateja's'g/wejgwateja's'g.html", "entry_url": "https://mikmaqonline.org/entries/w/wejgwateja's'g/wejgwateja's'g.html", "headword": "wejgwateja's'g", "example_index": 0, "raw_html_path": "raw/entries/a3038295c6bf453559308d6bb69735dd7d2bfbefe52804820d6efaef28e9195b.html", "raw_html_sha256": "d73379f005286cf77ebdfc77e65662c91b7034a958aafac7f1dd484f51294a75", "fetched_at": "2026-07-12T02:46:50.986Z", "recordings": [ { "recording_id": "90fe32f8c99ee251021b7bbe2cf5f69ef776da2ec8c7ea02da14a4bfa0f5220a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/84e/84ef012e1584b8df5504fd50bc5b60d4deac8d42690f31bd5d5908aeeccec00c.mp3", "archive_relative_path": "raw/audio/84e/84ef012e1584b8df5504fd50bc5b60d4deac8d42690f31bd5d5908aeeccec00c.mp3" } ] } ], "prediction": "Ango'te'l, mu te's'g'pugweg, na we'gwi'ji'j ta'n te'sijig.", "reference": "Ango'te'n, mut ugsam gigja'siw awti, teligsigawa's'g ala wejgwateja's'g." }, { "id": "mic-sent-70068d68efe6302e33d1a39c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That cannon fires a loud report.", "output_text": "Gesigawtewesigeg na tulgowei", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That cannon fires a loud report.", "mic_Latn": "Gesigawtewesigeg na tulgowei" }, "canonical_ref": "entries/g/gesigawtewesigeg/gesigawtewesigeg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-38241dc90d3a00035ff2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesigawtewesigeg/gesigawtewesigeg.html", "entry_url": "https://mikmaqonline.org/entries/g/gesigawtewesigeg/gesigawtewesigeg.html", "headword": "gesigawtewesigeg", "example_index": 0, "raw_html_path": "raw/entries/23301dfad131692d7b80a8dc7ffb7f6999451e1e2f66696eded17dd1a77ba56c.html", "raw_html_sha256": "db5e725486e4a19689d609fd316438add4c9fdea4c4f33ac703b64c4244bd274", "fetched_at": "2026-07-12T02:39:10.424Z", "recordings": [] } ], "prediction": "We'gwiga'toq na gmu'ji'j ta'n te's'g.", "reference": "Gesigawtewesigeg na tulgowei" }, { "id": "mic-sent-70325bd4965e98b9279fa2cc:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Smoked fish is very good (taste).", "output_text": "Puggwana'tasit nme'j mawwigapu'gsit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Smoked fish is very good (taste).", "mic_Latn": "Puggwana'tasit nme'j mawwigapu'gsit." }, "canonical_ref": "entries/p/puggwana'tasit_nme'j/puggwana'tasit_nme'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f86a9a383d19a2fc88fb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/puggwana'tasit_nme'j/puggwana'tasit_nme'j.html", "entry_url": "https://mikmaqonline.org/entries/p/puggwana'tasit_nme'j/puggwana'tasit_nme'j.html", "headword": "puggwana'tasit_nme'j", "example_index": 0, "raw_html_path": "raw/entries/b66178b1acdaa863c44fac47db45987a1a8849c54dd37892f90f28ce3433a9cf.html", "raw_html_sha256": "aa6bf03070785d85e0fd2f32f66268d28f9332470156307558350edbf835c00b", "fetched_at": "2026-07-12T02:44:20.661Z", "recordings": [ { "recording_id": "48ecd4d2c6a607f38bc8a403528392bd630f94703d8adbf0dc0e2cddba59f999", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3d1/3d11a4e89d7433cdc133ea4b30704d263b1e3537857b9c979d13a49ac0bfb159.mp3", "archive_relative_path": "raw/audio/3d1/3d11a4e89d7433cdc133ea4b30704d263b1e3537857b9c979d13a49ac0bfb159.mp3" } ] } ], "prediction": "We'gwi'jg na we'gwig.", "reference": "Puggwana'tasit nme'j mawwigapu'gsit." }, { "id": "mic-sent-708fcc1265e471e3a10ce5d9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she points the flag to the east.", "output_text": "Elasgng mtawegn ugjipenug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she points the flag to the east.", "mic_Latn": "Elasgng mtawegn ugjipenug." }, "canonical_ref": "entries/e/elasgng/elasgng.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4f17e137ac8fc88a146a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elasgng/elasgng.html", "entry_url": "https://mikmaqonline.org/entries/e/elasgng/elasgng.html", "headword": "elasgng", "example_index": 0, "raw_html_path": "raw/entries/d3cb476be3bcb80563b8f64a84c12a90f5828f2b5948c3345e95fff59c45f550.html", "raw_html_sha256": "dd3c38198ad7275f71fe2ba6d3301f60ce90f7353522a58b1d60d3d154f87c7c", "fetched_at": "2026-07-12T02:37:40.254Z", "recordings": [ { "recording_id": "5ecc4b2b887b0dace58266befecfe7bd9a4642f1b83ca8c32d0f33cb90945e2d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/58b/58beea4af40c364c90c8e4d9ee01c30adc51e4e10be9526d24782e3b1afe9810.mp3", "archive_relative_path": "raw/audio/58b/58beea4af40c364c90c8e4d9ee01c30adc51e4e10be9526d24782e3b1afe9810.mp3" } ] } ], "prediction": "We'gwi'g ugjit ala'toq.", "reference": "Elasgng mtawegn ugjipenug." }, { "id": "mic-sent-70b7540f3b0c12e1b89ebb70:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is exploiting that land he/she was given.", "output_text": "Sulieweie'gatg na maqamigew ignmut'p.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is exploiting that land he/she was given.", "mic_Latn": "Sulieweie'gatg na maqamigew ignmut'p." }, "canonical_ref": "entries/s/sulieweie'gatg/sulieweie'gatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8f27e9b0607da7a5f271", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sulieweie'gatg/sulieweie'gatg.html", "entry_url": "https://mikmaqonline.org/entries/s/sulieweie'gatg/sulieweie'gatg.html", "headword": "sulieweie'gatg", "example_index": 0, "raw_html_path": "raw/entries/623a7154636410fa4fba86f48ffcd9a562b7b3611d187640e1b3e160e91fdbe6.html", "raw_html_sha256": "a9767f556e732635689988369dd97748ffe0ca2c8698a9c207164baaa732d1e6", "fetched_at": "2026-07-12T02:45:16.733Z", "recordings": [ { "recording_id": "f64cdf6ef415af03d5d6b7e2c29ab03ac0fd8ab862c8263683cfef73b7718d99", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/63a/63a410976ae95d145e53e9435aa81f6453c811f0df5c9326738bb50c9f21dfd4.mp3", "archive_relative_path": "raw/audio/63a/63a410976ae95d145e53e9435aa81f6453c811f0df5c9326738bb50c9f21dfd4.mp3" } ] } ], "prediction": "Amujpa'latl na lpa wi'gatign.", "reference": "Sulieweie'gatg na maqamigew ignmut'p." }, { "id": "mic-sent-715b5b03b980a475b3efd6e3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Am I taking this the right way?", "output_text": "Tetapuiwgsua'tu na ula?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Am I taking this the right way?", "mic_Latn": "Tetapuiwgsua'tu na ula?" }, "canonical_ref": "entries/t/tetapuigsua'toq/tetapuigsua'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-81c062eb62659c1e13aa", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tetapuigsua'toq/tetapuigsua'toq.html", "entry_url": "https://mikmaqonline.org/entries/t/tetapuigsua'toq/tetapuigsua'toq.html", "headword": "tetapuigsua'toq", "example_index": 0, "raw_html_path": "raw/entries/f5629d46a04973fce5e452a911b06a0605aaea7d5685ae4a2ba96a59434d3538.html", "raw_html_sha256": "7c13f25f04c6726e3e97083f527a7088e66e62ff48982acfa85acf3a11e10e2e", "fetched_at": "2026-07-12T02:45:47.671Z", "recordings": [ { "recording_id": "0257bec2b1a76074dbaf4fb0d62e092fcd8388ea62fff70cba0f092408d0de90", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/80d/80dacc161ee79e0fe041d62483f4b4dd18696e0c18a4a6ace1bc811f796434c9.mp3", "archive_relative_path": "raw/audio/80d/80dacc161ee79e0fe041d62483f4b4dd18696e0c18a4a6ace1bc811f796434c9.mp3" } ] } ], "prediction": "Gi's gi'l na ula?", "reference": "Tetapuiwgsua'tu na ula?" }, { "id": "mic-sent-71c8b847a48c6fae6a6fbcc6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This dog has scared my child.", "output_text": "Ula nmu'j gisjipaqa'latl n'njann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This dog has scared my child.", "mic_Latn": "Ula nmu'j gisjipaqa'latl n'njann." }, "canonical_ref": "entries/j/jipaqa'latl/jipaqa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-180563a5abeb85c32f5e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jipaqa'latl/jipaqa'latl.html", "entry_url": "https://mikmaqonline.org/entries/j/jipaqa'latl/jipaqa'latl.html", "headword": "jipaqa'latl", "example_index": 0, "raw_html_path": "raw/entries/e66f4ef3b2047a3e8e0728e769d5d94baa739535124c9ca7d3fd6e526a81d0e3.html", "raw_html_sha256": "f2037d50321c207738301a140ed5592d9702b818850595b04732e010af32acdb", "fetched_at": "2026-07-12T02:40:25.736Z", "recordings": [ { "recording_id": "ab274d465ad4840e36295dd395bd4dac2bec958863ebb882645529d3f924a878", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/456/456a392501c8e9de555ffb0f8e7ef7c5580e0984c9b134add6466101e32c9a37.mp3", "archive_relative_path": "raw/audio/456/456a392501c8e9de555ffb0f8e7ef7c5580e0984c9b134add6466101e32c9a37.mp3" } ] } ], "prediction": "Ula nuji'j gesatg nitap.", "reference": "Ula nmu'j gisjipaqa'latl n'njann." }, { "id": "mic-sent-71ddb85c549e9306383fdfec:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she fells the trees toward (in the direction of) the shore.", "output_text": "Miti'sg eloqtesmaji sitmug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she fells the trees toward (in the direction of) the shore.", "mic_Latn": "Miti'sg eloqtesmaji sitmug." }, "canonical_ref": "entries/e/eloqtesmatl/eloqtesmatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-82c906dce6b4401660fd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/eloqtesmatl/eloqtesmatl.html", "entry_url": "https://mikmaqonline.org/entries/e/eloqtesmatl/eloqtesmatl.html", "headword": "eloqtesmatl", "example_index": 0, "raw_html_path": "raw/entries/22a138cc2a9c21f3a6626da98ab81c9e26db7d2525fc7bab4dda1fe98906338a.html", "raw_html_sha256": "c9397e21ecbdaf4244e3bdeac97cf221f866b92ffd731629e98e579e005ada01", "fetched_at": "2026-07-12T02:37:49.830Z", "recordings": [ { "recording_id": "7c931b85a69ff76f2456901bf82e6e6d5c12a7c217a75d4bdbe6c0b98f209589", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c77/c777ddfb57964f9116c7d8cd2e29686a17d7550da1eb96f8e0ef70e8219cdfed.mp3", "archive_relative_path": "raw/audio/c77/c777ddfb57964f9116c7d8cd2e29686a17d7550da1eb96f8e0ef70e8219cdfed.mp3" } ] } ], "prediction": "Pugwelg miti's'g ta'n tujiw.", "reference": "Miti'sg eloqtesmaji sitmug." }, { "id": "mic-sent-727d634a73962256d9fb1306:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The pigs will soon be fed.", "output_text": "Pugjig gulgwi'sg esmujig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The pigs will soon be fed.", "mic_Latn": "Pugjig gulgwi'sg esmujig." }, "canonical_ref": "entries/g/gulgwi's/gulgwi's.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dd9d48f75425a35a02a2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gulgwi's/gulgwi's.html", "entry_url": "https://mikmaqonline.org/entries/g/gulgwi's/gulgwi's.html", "headword": "gulgwi's", "example_index": 0, "raw_html_path": "raw/entries/4c9429df9d28b4300d9317eacd7cb1c1760f8227cef3c246f1a753e681cc0ea2.html", "raw_html_sha256": "015906f26fe9290131c89083e65d9e23c533b651dd598c82d29be0d06ddc4f7b", "fetched_at": "2026-07-12T02:39:59.768Z", "recordings": [ { "recording_id": "1ddcaf4243991c82820e4c0ac37162b9268bb2b8b981304c1a18954921d80f92", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/907/907c0dda0d5a9d2714023fa282576f20e737ae1dc10a5a2e3aa41541c5cfa7a7.mp3", "archive_relative_path": "raw/audio/907/907c0dda0d5a9d2714023fa282576f20e737ae1dc10a5a2e3aa41541c5cfa7a7.mp3" } ] } ], "prediction": "Pugwe'ji'j gaqami'j.", "reference": "Pugjig gulgwi'sg esmujig." }, { "id": "mic-sent-730709e5ba3e4b8b144c5d88:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A skunk is black and white.", "output_text": "Apigjilu na maqtaweg aq wape'g .", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A skunk is black and white.", "mic_Latn": "Apigjilu na maqtaweg aq wape'g ." }, "canonical_ref": "entries/a/apigjilu/apigjilu.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a5335338a0a244cad3e0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/apigjilu/apigjilu.html", "entry_url": "https://mikmaqonline.org/entries/a/apigjilu/apigjilu.html", "headword": "apigjilu", "example_index": 0, "raw_html_path": "raw/entries/9482edcf17f51427f35469be6eaa384b5e0b43c59e764895a3477670ffd3ad0e.html", "raw_html_sha256": "274476cd87bff6cdda44939263a80af2c4ed0856c855b7627d9eb1282adee960", "fetched_at": "2026-07-12T02:37:05.604Z", "recordings": [ { "recording_id": "bcb8207c8065d1f4eb6bfa062afc3c5472c06a6fa136a69be1c4b91c648c3cab", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fb5/fb53cfb2e1cb6fed822b97c3ac627b65087c875bb7c8d524c2724ff09549e15e.mp3", "archive_relative_path": "raw/audio/fb5/fb53cfb2e1cb6fed822b97c3ac627b65087c875bb7c8d524c2724ff09549e15e.mp3" } ] } ], "prediction": "Pugwe'g na we'gwi'g.", "reference": "Apigjilu na maqtaweg aq wape'g ." }, { "id": "mic-sent-7360fd116ecc378457b1c07a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Rotten meat really stinks.", "output_text": "Sugulegaq wius mawgesleg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Rotten meat really stinks.", "mic_Latn": "Sugulegaq wius mawgesleg." }, "canonical_ref": "entries/g/gesleg/gesleg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c3c4f4d1c1a5daef252c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesleg/gesleg.html", "entry_url": "https://mikmaqonline.org/entries/g/gesleg/gesleg.html", "headword": "gesleg", "example_index": 0, "raw_html_path": "raw/entries/0fa6d07acfe9b1fd9d24287383aa5b561c5f4dedd848685ba733f59f5743c281.html", "raw_html_sha256": "78f48cae2c9666af1aee1890d0279b690fa82c41fa32080510413cfc34bd4b22", "fetched_at": "2026-07-12T02:39:15.052Z", "recordings": [ { "recording_id": "9816e3c38c73ba357718d0fc9525763048bd9c0e717f9ab887b1a5c561962bbb", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/448/448488b9db33a4e566067d77baebc2f43529d134985a05cd674d64f80eeb6706.mp3", "archive_relative_path": "raw/audio/448/448488b9db33a4e566067d77baebc2f43529d134985a05cd674d64f80eeb6706.mp3" } ] } ], "prediction": "We'gwi'g na we'gwig.", "reference": "Sugulegaq wius mawgesleg." }, { "id": "mic-sent-7401357bb2a81ee09bcd2fc6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Go see my brother, he's the one who interprets.", "output_text": "Natnmi njignam, negm na nessutmalsewet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Go see my brother, he's the one who interprets.", "mic_Latn": "Natnmi njignam, negm na nessutmalsewet." }, "canonical_ref": "entries/n/nessutmalsewet/nessutmalsewet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2420d9c98d5094d0acc6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nessutmalsewet/nessutmalsewet.html", "entry_url": "https://mikmaqonline.org/entries/n/nessutmalsewet/nessutmalsewet.html", "headword": "nessutmalsewet", "example_index": 0, "raw_html_path": "raw/entries/a5fefeb25903b19c7e1cc9949f8028563a5ea1350f1e797ab143c5e62d8899f6.html", "raw_html_sha256": "7ba6fea2927c3e35417c7bcb25b7b7fd956b1cdb7a227da64013ecbb44eb9786", "fetched_at": "2026-07-12T02:42:23.260Z", "recordings": [ { "recording_id": "a2877272d9760b69d67f7654c04fdca0d79ffd87aee2385930002e97fdf02ed7", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b94/b94c0ade95819a178171359c023ec9d51c14f73e970c3069f27f68164955f170.mp3", "archive_relative_path": "raw/audio/b94/b94c0ade95819a178171359c023ec9d51c14f73e970c3069f27f68164955f170.mp3" } ] } ], "prediction": "Ge' gi'l nitap nitap, e'w ta'n te's'g.", "reference": "Natnmi njignam, negm na nessutmalsewet." }, { "id": "mic-sent-7465bda328cc4b2fd5aeb50e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Too bad that the church burned, it was so old.", "output_text": "Amsaloqte'g na a's'tuo'guomeg, telsa'qaweieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Too bad that the church burned, it was so old.", "mic_Latn": "Amsaloqte'g na a's'tuo'guomeg, telsa'qaweieg." }, "canonical_ref": "entries/a/amsaloqteg/amsaloqteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4d7685320f0d9215ee0a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amsaloqteg/amsaloqteg.html", "entry_url": "https://mikmaqonline.org/entries/a/amsaloqteg/amsaloqteg.html", "headword": "amsaloqteg", "example_index": 0, "raw_html_path": "raw/entries/76126b9d09b18516a5b25e74103a8043c85c1a01cf0dc92a6bcb589e95718935.html", "raw_html_sha256": "2d62c2eb5982f13a639a2208d4b8058e4b8bb67a3c4cbdedb72fa547caba75bb", "fetched_at": "2026-07-12T02:36:55.838Z", "recordings": [ { "recording_id": "1ffd7d235745a8d28b661f0e3de38c45aa7c95617f617e905555b9109a7123bf", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8a3/8a34896599df4babdf5f337a24b729bae4b5bf2e59816162c1dc0028c2067acf.mp3", "archive_relative_path": "raw/audio/8a3/8a34896599df4babdf5f337a24b729bae4b5bf2e59816162c1dc0028c2067acf.mp3" } ] } ], "prediction": "Te's'g na lpa wi'gwi'gig, te's te'sijig.", "reference": "Amsaloqte'g na a's'tuo'guomeg, telsa'qaweieg." }, { "id": "mic-sent-751dd137fc0246f563291552:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Now that is the first time I see a mirror crack from heat!", "output_text": "Na gatu amsgwes nemitu plu'jaqamati pasginoqteg!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Now that is the first time I see a mirror crack from heat!", "mic_Latn": "Na gatu amsgwes nemitu plu'jaqamati pasginoqteg!" }, "canonical_ref": "entries/p/pasginoqteg/pasginoqteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0c3ea7b2c35174b4b084", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pasginoqteg/pasginoqteg.html", "entry_url": "https://mikmaqonline.org/entries/p/pasginoqteg/pasginoqteg.html", "headword": "pasginoqteg", "example_index": 0, "raw_html_path": "raw/entries/2176856cb6569e3dc14128b17849e9325bf6989acd70f992150e8d3f561c0b18.html", "raw_html_sha256": "8faf50b3f416389d85324f59a9abe2b3b531adeaf30b1bdbe3486d3fb30fab50", "fetched_at": "2026-07-12T02:43:14.625Z", "recordings": [ { "recording_id": "dca674e39e017460ae94c5540da4c37292e934a018833ec0e7a9a1cb2595b6bc", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/936/93682e5f0d6a3d89ab56e36f056239d69c205087be66467099ebeea247a70363.mp3", "archive_relative_path": "raw/audio/936/93682e5f0d6a3d89ab56e36f056239d69c205087be66467099ebeea247a70363.mp3" } ] } ], "prediction": "Nige' na nige' newte'n nugu' gmu'ji'j!", "reference": "Na gatu amsgwes nemitu plu'jaqamati pasginoqteg!" }, { "id": "mic-sent-752e6690488a390e0ab4acda:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My grandchild bore a child yesterday.", "output_text": "Nuji'j we'ji'wet ulagu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My grandchild bore a child yesterday.", "mic_Latn": "Nuji'j we'ji'wet ulagu." }, "canonical_ref": "entries/w/we'ji'wet/we'ji'wet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-661f1c740982e08c834b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/we'ji'wet/we'ji'wet.html", "entry_url": "https://mikmaqonline.org/entries/w/we'ji'wet/we'ji'wet.html", "headword": "we'ji'wet", "example_index": 0, "raw_html_path": "raw/entries/2568341879927be8b0198de1a0a10041b511dad7090f3299d2079bf9eec61c79.html", "raw_html_sha256": "633b0c31317b4f21de9a8bf6ea7b90a018b5e7a46467b805506b12d643c5ccd5", "fetched_at": "2026-07-12T02:46:55.665Z", "recordings": [ { "recording_id": "5dbd01c2890bb7dfad0c4747c8725a6c29fe2f265a1cca85f920ebd497534753", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e56/e567d4d73458a197529466ff17219d7da50aedf9ed7778a2a1e23be6c98f31ec.mp3", "archive_relative_path": "raw/audio/e56/e567d4d73458a197529466ff17219d7da50aedf9ed7778a2a1e23be6c98f31ec.mp3" } ] } ], "prediction": "Nuji'j gesatg ulagu.", "reference": "Nuji'j we'ji'wet ulagu." }, { "id": "mic-sent-75523e3658aed87c18a5ee6e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is at it now, smoking the salmon.", "output_text": "Wesgowa'sit nige', plamu'g etlpuggwana'laji.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is at it now, smoking the salmon.", "mic_Latn": "Wesgowa'sit nige', plamu'g etlpuggwana'laji." }, "canonical_ref": "entries/p/puggwana'latl/puggwana'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-51ec546c833c91fcc93a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/puggwana'latl/puggwana'latl.html", "entry_url": "https://mikmaqonline.org/entries/p/puggwana'latl/puggwana'latl.html", "headword": "puggwana'latl", "example_index": 0, "raw_html_path": "raw/entries/bda2b3974d393f0f3f96337232b6ac633c98393c955ee3cdad46abf804b6ff85.html", "raw_html_sha256": "847a9a6bede65d0b77429750fcfc46067c03bf27fd8845c943fea0b5a1382a83", "fetched_at": "2026-07-12T02:44:20.444Z", "recordings": [ { "recording_id": "88fa14e38855127c290b9e9a71916384ddfadaa09d63bbec471bc20e37d1e14b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/834/83453fdc4554235784a7ddb012ab4673fdd75f5ea305d41e08a7ab016818182a.mp3", "archive_relative_path": "raw/audio/834/83453fdc4554235784a7ddb012ab4673fdd75f5ea305d41e08a7ab016818182a.mp3" } ] } ], "prediction": "Ni'n gi's nige', plamu'g.", "reference": "Wesgowa'sit nige', plamu'g etlpuggwana'laji." }, { "id": "mic-sent-756ce9c1059b3a2255835d41:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I don't know if this word \"sgweioq\" (female animal) is used here in Listuguj.", "output_text": "Mu ge'itu ula glusuaqan \"sgweioq\" Listugujg e'was'tn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I don't know if this word \"sgweioq\" (female animal) is used here in Listuguj.", "mic_Latn": "Mu ge'itu ula glusuaqan \"sgweioq\" Listugujg e'was'tn." }, "canonical_ref": "entries/s/sgweioq/sgweioq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-880a9c942c793041eeef", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sgweioq/sgweioq.html", "entry_url": "https://mikmaqonline.org/entries/s/sgweioq/sgweioq.html", "headword": "sgweioq", "example_index": 0, "raw_html_path": "raw/entries/6d2b7aed70d83ed663fb5e00fce51813079ab1705673f629f634902a1677b2e5.html", "raw_html_sha256": "18cc2cd2784976155aff340c0c79f5b008821bbeb62ffd2c4ac831b2dbcd3779", "fetched_at": "2026-07-12T02:44:58.732Z", "recordings": [ { "recording_id": "aeffd6b394a7142b1228a33c4b827652934ca428b87a30ba6a05cae759c17f32", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/eae/eae4f88d1cdf139b5a2f78bf2a7e9fcf543f8bdbe136a642b920c7cf4cfbb61d.mp3", "archive_relative_path": "raw/audio/eae/eae4f88d1cdf139b5a2f78bf2a7e9fcf543f8bdbe136a642b920c7cf4cfbb61d.mp3" } ] } ], "prediction": "Mu gejiaq ula \"sgweioq\" ta'n tujiw Listugujg.", "reference": "Mu ge'itu ula glusuaqan \"sgweioq\" Listugujg e'was'tn." }, { "id": "mic-sent-7577ca51d7d9c8561ed3459f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Do you know a story that talks about ghosts?", "output_text": "Nenmn a'tugwaqan ta'n wesgumaji sg'te'gmujg?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Do you know a story that talks about ghosts?", "mic_Latn": "Nenmn a'tugwaqan ta'n wesgumaji sg'te'gmujg?" }, "canonical_ref": "entries/s/sg'te'gmuj/sg'te'gmuj.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b9f1fea95bc16a21da55", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sg'te'gmuj/sg'te'gmuj.html", "entry_url": "https://mikmaqonline.org/entries/s/sg'te'gmuj/sg'te'gmuj.html", "headword": "sg'te'gmuj", "example_index": 0, "raw_html_path": "raw/entries/b0d44e460c442327134a150ee165fddcfce28b83536dcca31057620228af54a1.html", "raw_html_sha256": "bd9e8c085e9ce1e279728c2fb475e72d7daed546911c7344a605f9c01733368f", "fetched_at": "2026-07-12T02:44:58.350Z", "recordings": [ { "recording_id": "6dc28fd5cb245f0ec358de013e3ce9e30905bebb041378e8106bdf64065ee6a5", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/da3/da3ba9d1d861a87ad867cd7c3870d015c6d06d0d2715d30649807b9e954804e3.mp3", "archive_relative_path": "raw/audio/da3/da3ba9d1d861a87ad867cd7c3870d015c6d06d0d2715d30649807b9e954804e3.mp3" } ] } ], "prediction": "Ge' gi's gi'l ta'n te'sipow muta gmu'j?", "reference": "Nenmn a'tugwaqan ta'n wesgumaji sg'te'gmujg?" }, { "id": "mic-sent-75df344e5e0cb4955c48551e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she stands it straight like a statue.", "output_text": "Tetpaqqama'latl st'ge nnuoqta'wul.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she stands it straight like a statue.", "mic_Latn": "Tetpaqqama'latl st'ge nnuoqta'wul." }, "canonical_ref": "entries/t/tetpaqqama'latl/tetpaqqama'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-255e422f15f03866b8a7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tetpaqqama'latl/tetpaqqama'latl.html", "entry_url": "https://mikmaqonline.org/entries/t/tetpaqqama'latl/tetpaqqama'latl.html", "headword": "tetpaqqama'latl", "example_index": 0, "raw_html_path": "raw/entries/eb9bec9a5b38a8f20c1885a119ecbc33516deb7076833da183f3d08543353851.html", "raw_html_sha256": "b186aae4e3773c90982533b697c0cfa6882eddd2cffa1e1f7906514c72c06196", "fetched_at": "2026-07-12T02:45:50.380Z", "recordings": [ { "recording_id": "694ba4a48a0093e23ae920b1552551f5af00a2f9d526010280e22b0fc5cbcc1d", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5f4/5f44fabb5f7e2730522fb4a5057d33085ce4853dc234dbdabbf1696fc829eb3f.mp3", "archive_relative_path": "raw/audio/5f4/5f44fabb5f7e2730522fb4a5057d33085ce4853dc234dbdabbf1696fc829eb3f.mp3" } ] } ], "prediction": "Gesatg ta'n tujiw gmu'j.", "reference": "Tetpaqqama'latl st'ge nnuoqta'wul." }, { "id": "mic-sent-7607c4a8add2332d0fc4b344:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Again Joseph let the fire die out, I'll have to build another fire in the stove again.", "output_text": "Gi's ap naqasuenmat na So'sep, amujpa ap mugsa'l'g ula epsaqtejg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Again Joseph let the fire die out, I'll have to build another fire in the stove again.", "mic_Latn": "Gi's ap naqasuenmat na So'sep, amujpa ap mugsa'l'g ula epsaqtejg." }, "canonical_ref": "entries/m/mawsa'latl/mawsa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1753a713ce1902177c82", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mawsa'latl/mawsa'latl.html", "entry_url": "https://mikmaqonline.org/entries/m/mawsa'latl/mawsa'latl.html", "headword": "mawsa'latl", "example_index": 0, "raw_html_path": "raw/entries/edf3fc20bb9ff982d44b60c58fa515831ee1a774faf3eee8e7b546edaa289667.html", "raw_html_sha256": "1ba896e4ecc0b247f62cfb1f030b9ec89e613c5b45e1451c5f6ddda105f41fc0", "fetched_at": "2026-07-12T02:41:03.932Z", "recordings": [ { "recording_id": "899d624dc2b8bf8985a3e64324cc8d1a32e6f13ce0fc44d7ea9233f90a945ffd", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/286/2865d5a300190c255c947b86c57d31bd9c5ab9f161a15cf80d9bb9e5bc6bc8ed.mp3", "archive_relative_path": "raw/audio/286/2865d5a300190c255c947b86c57d31bd9c5ab9f161a15cf80d9bb9e5bc6bc8ed.mp3" } ] } ], "prediction": "Gi's'p newte' So'sep gmu'j, amujpa nige' newtepa'toq ugta'qann.", "reference": "Gi's ap naqasuenmat na So'sep, amujpa ap mugsa'l'g ula epsaqtejg." }, { "id": "mic-sent-76cdb13a4901e4ad7a39b55b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who's house is that at the front?", "output_text": "Wen ala wiguow e'tmateg?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who's house is that at the front?", "mic_Latn": "Wen ala wiguow e'tmateg?" }, "canonical_ref": "entries/e/e'tmateg/e'tmateg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8339e002167a9b460424", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/e'tmateg/e'tmateg.html", "entry_url": "https://mikmaqonline.org/entries/e/e'tmateg/e'tmateg.html", "headword": "e'tmateg", "example_index": 0, "raw_html_path": "raw/entries/8a500979195d09549c524815800e5d320fb25715472e26d2b032606030c3536c.html", "raw_html_sha256": "d9f4cd98eb99c0132f398f243194a8c1ff133040394f98d56bd96da0abb2c763", "fetched_at": "2026-07-12T02:38:26.213Z", "recordings": [ { "recording_id": "671f2d55456c7430a42c35815c681a18d89fa0310d610fab2a12e74992f35c46", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/59a/59a05a9b205b3a744a88ec1dc8aab0e282cee0e1f9e9c2a2489bf1173ff1a94a.mp3", "archive_relative_path": "raw/audio/59a/59a05a9b205b3a744a88ec1dc8aab0e282cee0e1f9e9c2a2489bf1173ff1a94a.mp3" } ] } ], "prediction": "Wen na wenji'j na ta'n tujiw?", "reference": "Wen ala wiguow e'tmateg?" }, { "id": "mic-sent-7725be0ba8def63b23315fe4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The embers still give off light.", "output_text": "Me' wasoqonewegl na pugsaqatal.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The embers still give off light.", "mic_Latn": "Me' wasoqonewegl na pugsaqatal." }, "canonical_ref": "entries/w/wasoqonaweg/wasoqonaweg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9c7c87bc9411bfce55e1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wasoqonaweg/wasoqonaweg.html", "entry_url": "https://mikmaqonline.org/entries/w/wasoqonaweg/wasoqonaweg.html", "headword": "wasoqonaweg", "example_index": 0, "raw_html_path": "raw/entries/61d85a219312c97438c91fa5261ed22a79f63a44808831c0f6d9fec4ba558372.html", "raw_html_sha256": "b7567dbaf95ff1127653221d5115590371d1dee6d429c942096aba1a99985cf2", "fetched_at": "2026-07-12T02:46:42.150Z", "recordings": [ { "recording_id": "5e0011cfa0d6bd72bf3f1750d1c5fa59e07d2e7bd0c9016d5e90af045ea7bed9", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/410/41006f26b03744c52753f4377a31de155e64d2021dc291819b7d56e373a54fb6.mp3", "archive_relative_path": "raw/audio/410/41006f26b03744c52753f4377a31de155e64d2021dc291819b7d56e373a54fb6.mp3" } ] } ], "prediction": "Pugwe'g ta'n tujiw gmu'j.", "reference": "Me' wasoqonewegl na pugsaqatal." }, { "id": "mic-sent-79102da9393c379993347d5c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Have you seen a headless man?", "output_text": "Gis gi'l nemi't ji'nm temgwe'g?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Have you seen a headless man?", "mic_Latn": "Gis gi'l nemi't ji'nm temgwe'g?" }, "canonical_ref": "entries/t/temgwe'g/temgwe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ea89ad0e82f2d8fb24ef", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/temgwe'g/temgwe'g.html", "entry_url": "https://mikmaqonline.org/entries/t/temgwe'g/temgwe'g.html", "headword": "temgwe'g", "example_index": 0, "raw_html_path": "raw/entries/66b212d8be457d6f6b166dd5ddb471fda4a31a232b1186f6820c5e3160b9e7a5.html", "raw_html_sha256": "ca8097902067a9e69f15f35b3e7293bdab51d0e40ba490f9a487cebfaf221112", "fetched_at": "2026-07-12T02:45:37.626Z", "recordings": [ { "recording_id": "35284888818a47f39a11e3e5f9a6298a694e995fb7549242589d757833a54291", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/929/929c5e54919a2a87383d336163c165c0050cc4ea4f689d4d443ec1fab50e8fac.mp3", "archive_relative_path": "raw/audio/929/929c5e54919a2a87383d336163c165c0050cc4ea4f689d4d443ec1fab50e8fac.mp3" } ] } ], "prediction": "Gi's gi'l nemi'g ji'nm?", "reference": "Gis gi'l nemi't ji'nm temgwe'g?" }, { "id": "mic-sent-792e5bc3fcfaa79e2251eb9f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My eye is watery and I have a headache.", "output_text": "Samuqwaniaq npugug aq nunji gesnuguig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My eye is watery and I have a headache.", "mic_Latn": "Samuqwaniaq npugug aq nunji gesnuguig." }, "canonical_ref": "entries/s/samuqwaniaq/samuqwaniaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f5a200e6014a44d8d5d7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/samuqwaniaq/samuqwaniaq.html", "entry_url": "https://mikmaqonline.org/entries/s/samuqwaniaq/samuqwaniaq.html", "headword": "samuqwaniaq", "example_index": 0, "raw_html_path": "raw/entries/11f01137c8d876a572e99c7fd7056e5ec03f3e2a9165b0efa6b04636786cdfd8.html", "raw_html_sha256": "2b52d592c7224f349c23d8ae83f422c957787c61489ffee1fe02be3ee5597e38", "fetched_at": "2026-07-12T02:44:36.114Z", "recordings": [ { "recording_id": "1acd657fbe8451f22b1dd8cc30bcc6cadf9a8d3bafd8bfe2b644530b079ffef0", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dbb/dbb06f9e8043fe4d3479c1cfd23694faaa3f31f4d3805cdb2f1a2f5bebebb0b2.mp3", "archive_relative_path": "raw/audio/dbb/dbb06f9e8043fe4d3479c1cfd23694faaa3f31f4d3805cdb2f1a2f5bebebb0b2.mp3" } ] } ], "prediction": "Mi'j na'te'g aq nugu's'g.", "reference": "Samuqwaniaq npugug aq nunji gesnuguig." }, { "id": "mic-sent-79c370652b65ade69e0c837a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where you are the water flows clear.", "output_text": "Waqamitg na ta'n wesgowa'sin.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where you are the water flows clear.", "mic_Latn": "Waqamitg na ta'n wesgowa'sin." }, "canonical_ref": "entries/w/waqamitg/waqamitg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bc88a3291284037dda60", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waqamitg/waqamitg.html", "entry_url": "https://mikmaqonline.org/entries/w/waqamitg/waqamitg.html", "headword": "waqamitg", "example_index": 0, "raw_html_path": "raw/entries/99f5feeb7b4526319202dd6981fe70ef23e82e312518d6bca8a1639bf2234fe7.html", "raw_html_sha256": "e31001f07b596f67264475291fad4d8fd7992a2e39f9fd420cfb819711ffe56f", "fetched_at": "2026-07-12T02:46:38.631Z", "recordings": [ { "recording_id": "5938373390f334f9483cd51c5436531c3c5658d4ca84b7f246766b25aee15fc1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/961/961affd6caab469176859b68d9dcf9495bd28b002fd23eb44dcc5d8550127366.mp3", "archive_relative_path": "raw/audio/961/961affd6caab469176859b68d9dcf9495bd28b002fd23eb44dcc5d8550127366.mp3" } ] } ], "prediction": "Ta'n tujiw e'w'g ta'n te'sijig.", "reference": "Waqamitg na ta'n wesgowa'sin." }, { "id": "mic-sent-79d0c436b0a3a338703f65fa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she takes everything downstairs before leaving.", "output_text": "Ms't goqwei nisa'toq gesgmnaq maja'sigw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she takes everything downstairs before leaving.", "mic_Latn": "Ms't goqwei nisa'toq gesgmnaq maja'sigw." }, "canonical_ref": "entries/n/nisa'toq/nisa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-570b6e9837861814c48c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nisa'toq/nisa'toq.html", "entry_url": "https://mikmaqonline.org/entries/n/nisa'toq/nisa'toq.html", "headword": "nisa'toq", "example_index": 0, "raw_html_path": "raw/entries/2a0a12747973283efffb62abb4f005e2666d8f71b4601714792b82376dccb1be.html", "raw_html_sha256": "b4655fd98a7d1fc2220d344d115fb5a8b1d32787a58197f1bd417b691f69f37a", "fetched_at": "2026-07-12T02:42:36.419Z", "recordings": [ { "recording_id": "3a254a6a2dff2c05f58d56e7fb054d34c400cf43e2a1ac40e8eb30493c373e10", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b1d/b1d8d5efec636ec1f67b9a5876806035ee4b1dc13e68feec6bf090bb2a64efe1.mp3", "archive_relative_path": "raw/audio/b1d/b1d8d5efec636ec1f67b9a5876806035ee4b1dc13e68feec6bf090bb2a64efe1.mp3" } ] } ], "prediction": "Pugwelg ta'n te's'g goqwei gesgmnaq gisijig.", "reference": "Ms't goqwei nisa'toq gesgmnaq maja'sigw." }, { "id": "mic-sent-7a005d3be6955a91f33a9348:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My son has a fancy fish bowl.", "output_text": "Nwis geggunatl mo'qiginitl nme'juo'ql.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My son has a fancy fish bowl.", "mic_Latn": "Nwis geggunatl mo'qiginitl nme'juo'ql." }, "canonical_ref": "entries/n/nme'juo'q/nme'juo'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-61056dbe63fe6750971c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nme'juo'q/nme'juo'q.html", "entry_url": "https://mikmaqonline.org/entries/n/nme'juo'q/nme'juo'q.html", "headword": "nme'juo'q", "example_index": 0, "raw_html_path": "raw/entries/9a70e495d5c178153d85546447f64fcbcb545171202443bfd3d25e140bb2222e.html", "raw_html_sha256": "ea0692d507dc23d2d3476a19fda7e29871a38029acd4f7b93cb6e97cf25ab088", "fetched_at": "2026-07-12T02:42:40.447Z", "recordings": [ { "recording_id": "554cc91c59f52695e65b9436102454164154e682ce29706f6663c1d68bd41eef", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/328/3286e8357f55b8b77911d0d43f6373eee7461204afa4b91cfe801f271e6fa203.mp3", "archive_relative_path": "raw/audio/328/3286e8357f55b8b77911d0d43f6373eee7461204afa4b91cfe801f271e6fa203.mp3" } ] } ], "prediction": "Ngwis e'pite'g na wi'gwi'g.", "reference": "Nwis geggunatl mo'qiginitl nme'juo'ql." }, { "id": "mic-sent-7a63e111080d02ef04587420:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That candle over there, the short and round one, please pass it over to me?", "output_text": "Wasoqonmaqan ala eteg, toqwapsgeg, ge' jugwasga'tui?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That candle over there, the short and round one, please pass it over to me?", "mic_Latn": "Wasoqonmaqan ala eteg, toqwapsgeg, ge' jugwasga'tui?" }, "canonical_ref": "entries/t/toqopsgeg/toqopsgeg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f392d76fdd4cfdbe3e49", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/toqopsgeg/toqopsgeg.html", "entry_url": "https://mikmaqonline.org/entries/t/toqopsgeg/toqopsgeg.html", "headword": "toqopsgeg", "example_index": 0, "raw_html_path": "raw/entries/487af0ff092854a8e7755adce7bccbe125be79a1a89ed6bd124e437a823a7c30.html", "raw_html_sha256": "fcfcbb7d85bc702c4c347f59b793c94594273d1dfec0db14ff2485712a1f0d2d", "fetched_at": "2026-07-12T02:46:03.555Z", "recordings": [ { "recording_id": "285ff438f3e76159411eaa73f799be1630e7390391df86834e5188f6c5eccd2e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/657/6575e55c2ee2e8a8fc04afae80cceb26ad668f67b9f3148df4d1c34812d1fb5a.mp3", "archive_relative_path": "raw/audio/657/6575e55c2ee2e8a8fc04afae80cceb26ad668f67b9f3148df4d1c34812d1fb5a.mp3" } ] } ], "prediction": "Ala gmu'ji'j na ala, lpa mesgi'j, ge' jugwa'tu'n?", "reference": "Wasoqonmaqan ala eteg, toqwapsgeg, ge' jugwasga'tui?" }, { "id": "mic-sent-7ac46d0a9e35bd8fcf58a21a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This lobster is dry.", "output_text": "Ula jagej na gispasit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This lobster is dry.", "mic_Latn": "Ula jagej na gispasit." }, "canonical_ref": "entries/g/gispasit/gispasit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b5f089f3272358d13d73", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gispasit/gispasit.html", "entry_url": "https://mikmaqonline.org/entries/g/gispasit/gispasit.html", "headword": "gispasit", "example_index": 0, "raw_html_path": "raw/entries/3cddceefef24e19be56ba4514845f8b9be5ae9cf9987bdd57f4e6f401b8acf3f.html", "raw_html_sha256": "a9ecdb89d08337cd1b39033d95d9b593776b49cc7dbc0d704541834411a17f22", "fetched_at": "2026-07-12T02:39:41.988Z", "recordings": [ { "recording_id": "eac782761faeb57dcce0e3d3a083e6090332e336cd87235d42dfbaf1c6eb791e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e1e/e1ed5ba50f7af8e3736700295d9a765b392f9ead86a9f6b9ebd0664f64c6273b.mp3", "archive_relative_path": "raw/audio/e1e/e1ed5ba50f7af8e3736700295d9a765b392f9ead86a9f6b9ebd0664f64c6273b.mp3" } ] } ], "prediction": "Ula gmu'ji'j etli'g.", "reference": "Ula jagej na gispasit." }, { "id": "mic-sent-7ad56d71a10511fe8a4dc554:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Enough already, he/she has wreaked too much revenge.", "output_text": "Nugu' na wasmiasita'teget.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Enough already, he/she has wreaked too much revenge.", "mic_Latn": "Nugu' na wasmiasita'teget." }, "canonical_ref": "entries/a/asita'teget/asita'teget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-485d0ae27986bf5ec85a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/asita'teget/asita'teget.html", "entry_url": "https://mikmaqonline.org/entries/a/asita'teget/asita'teget.html", "headword": "asita'teget", "example_index": 0, "raw_html_path": "raw/entries/afd3456300886ca3b93c6e5d92a1b2f2e7d722811e1b62ab527b6e514b9deeae.html", "raw_html_sha256": "4b9ae5e49af125548987450dc521a84e995abd36f7ff1c26bb5f6c97d97ae10a", "fetched_at": "2026-07-12T02:37:20.830Z", "recordings": [ { "recording_id": "a507bd300a3aea0996c4fe5142ed3571e395d0b1f4ba151d5b48859fb1ad06de", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/97d/97d2766451997c1fd72d0ee09a36cae7a6033ea992d8b2dfbf21ea9ade03a82c.mp3", "archive_relative_path": "raw/audio/97d/97d2766451997c1fd72d0ee09a36cae7a6033ea992d8b2dfbf21ea9ade03a82c.mp3" } ] } ], "prediction": "Gi's gi's, te's'g gisga'sit.", "reference": "Nugu' na wasmiasita'teget." }, { "id": "mic-sent-7af6cbed4bb47dfcf1e2f5b7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Is that a bird I hear fluttering?", "output_text": "Jipji'j na metewaqsing?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Is that a bird I hear fluttering?", "mic_Latn": "Jipji'j na metewaqsing?" }, "canonical_ref": "entries/m/metewaqsing/metewaqsing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3a6bb30bd4d00842f035", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/metewaqsing/metewaqsing.html", "entry_url": "https://mikmaqonline.org/entries/m/metewaqsing/metewaqsing.html", "headword": "metewaqsing", "example_index": 0, "raw_html_path": "raw/entries/e55a546b418f7a708286b2062a8bcfe27dfc2f60947c564ac6b574f34a9d992c.html", "raw_html_sha256": "d4e21c094f15ce8bf60def83e5f7cf4b960b5c56311993006c2e2c1c4ec29e61", "fetched_at": "2026-07-12T02:41:26.185Z", "recordings": [ { "recording_id": "9315d4a1bb01d6a571d59a925e608237e306dccc6e354a57d9482b03cb772381", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/460/46039fa30e677c7d9fdf94b675ca6597ab5d70d29a6994045d96bd94ef8bb22a.mp3", "archive_relative_path": "raw/audio/460/46039fa30e677c7d9fdf94b675ca6597ab5d70d29a6994045d96bd94ef8bb22a.mp3" } ] } ], "prediction": "Ge' na nuji'j etlugowa'latl?", "reference": "Jipji'j na metewaqsing?" }, { "id": "mic-sent-7b0f365bf405ff55ef2a5163:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Each time I lend him/her my axe he/she fractures the handle.", "output_text": "Te's maqata'g nutmi'gn na temtestoq lnaqanatgw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Each time I lend him/her my axe he/she fractures the handle.", "mic_Latn": "Te's maqata'g nutmi'gn na temtestoq lnaqanatgw." }, "canonical_ref": "entries/t/temtestoq/temtestoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ca7717e15991e1c82ca7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/temtestoq/temtestoq.html", "entry_url": "https://mikmaqonline.org/entries/t/temtestoq/temtestoq.html", "headword": "temtestoq", "example_index": 0, "raw_html_path": "raw/entries/ad0f61316859147e0e035e6e32fb34e52fd63baaca3a36a2d17267078e861c00.html", "raw_html_sha256": "22e9a6126b54f6b878c86f18a1e67465f67a231880906156f27a25e346b78403", "fetched_at": "2026-07-12T02:45:40.433Z", "recordings": [ { "recording_id": "5bc5d24eb10b8e7060c74f6fa9690dd177a7016b608dca89c2689d5ddb5c121b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3e9/3e95f6e9a9acb80b9e6ce0c3298538a28e204ab80d907a7f98f81158887a5576.mp3", "archive_relative_path": "raw/audio/3e9/3e95f6e9a9acb80b9e6ce0c3298538a28e204ab80d907a7f98f81158887a5576.mp3" } ] } ], "prediction": "Te's ta'n tujiw nmu'j gmu'ji'j etlmesg'g.", "reference": "Te's maqata'g nutmi'gn na temtestoq lnaqanatgw." }, { "id": "mic-sent-7b15b51da68fbe76a8f2a516:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little bear is always ready lick any sweet liquid.", "output_text": "Mui'ne'j pas'g epit sismo'qonapu musgwatmn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little bear is always ready lick any sweet liquid.", "mic_Latn": "Mui'ne'j pas'g epit sismo'qonapu musgwatmn." }, "canonical_ref": "entries/m/musgwatg/musgwatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-76c20e6e10005963e4df", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/musgwatg/musgwatg.html", "entry_url": "https://mikmaqonline.org/entries/m/musgwatg/musgwatg.html", "headword": "musgwatg", "example_index": 0, "raw_html_path": "raw/entries/0f1c48681953d76d9efc5660d89bbf19dd91c61382d514d3f175654f3298c792.html", "raw_html_sha256": "e808fe5d00085027fdffaf5d90f907047ac7b8721b7e5d1487662dd777b9ae78", "fetched_at": "2026-07-12T02:41:51.057Z", "recordings": [ { "recording_id": "752c8717db3291899988c6a9900f756a8dc5e7d6268491e9c5a2ccf3f1933bff", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/efe/efe4cc0da32be0720ad2484ed863ce523e9be342674b153281cf081e25ec5263.mp3", "archive_relative_path": "raw/audio/efe/efe4cc0da32be0720ad2484ed863ce523e9be342674b153281cf081e25ec5263.mp3" } ] } ], "prediction": "E'pite'ji'j na te'sipo'q te's'g ta'n tujiw maljewe'jg.", "reference": "Mui'ne'j pas'g epit sismo'qonapu musgwatmn." }, { "id": "mic-sent-7b339cfe6db53e022a40e572:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "We walked in to the brightest house.", "output_text": "Pisgwitaieg wenji'guom ta'n mawpitiateg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "We walked in to the brightest house.", "mic_Latn": "Pisgwitaieg wenji'guom ta'n mawpitiateg." }, "canonical_ref": "entries/p/pitiateg/pitiateg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-def4c6eb7c30fd113d71", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pitiateg/pitiateg.html", "entry_url": "https://mikmaqonline.org/entries/p/pitiateg/pitiateg.html", "headword": "pitiateg", "example_index": 0, "raw_html_path": "raw/entries/60cbbbcedd1be7df50aaaed92e7eec59b798cc8ed6559de679033e4721deeb75.html", "raw_html_sha256": "2d8414834c40b45dc2f61bd8e8c2a0c0601602b35a6e5a0f13311f249327acad", "fetched_at": "2026-07-12T02:44:08.090Z", "recordings": [ { "recording_id": "b492e0950535884cd2cb5bbf240c01bd2e492dfeada38db91ae9cb2fc310c6be", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/327/3275184cde94102a3c8a107ec779b6e1b6d3d03ce792706e01741ff8588f1acd.mp3", "archive_relative_path": "raw/audio/327/3275184cde94102a3c8a107ec779b6e1b6d3d03ce792706e01741ff8588f1acd.mp3" } ] } ], "prediction": "Pugwelg'p't'p na gmu'j.", "reference": "Pisgwitaieg wenji'guom ta'n mawpitiateg." }, { "id": "mic-sent-7bd2ec7765484a85fecbaa5b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "David, he is a good cook.", "output_text": "Ta'pit, na negm nata'wisugwateget.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "David, he is a good cook.", "mic_Latn": "Ta'pit, na negm nata'wisugwateget." }, "canonical_ref": "entries/n/nata'wisugwateget/nata'wisugwateget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-df9dcb73d6c99d1fde7b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nata'wisugwateget/nata'wisugwateget.html", "entry_url": "https://mikmaqonline.org/entries/n/nata'wisugwateget/nata'wisugwateget.html", "headword": "nata'wisugwateget", "example_index": 0, "raw_html_path": "raw/entries/cebbfa57f0a315626a937dc4facd2cc00921799fffcdd36311c46d7f86d473a9.html", "raw_html_sha256": "de212250344376c8bda70ac98da464093df2337140eaf15e2cd9e6e4f0c0e9ce", "fetched_at": "2026-07-12T02:42:12.095Z", "recordings": [ { "recording_id": "1c2977b7cfc7e2a064a9b3702fde221ab5fb0709f21c4f92ff586e36f8dc4492", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b5e/b5ea6c5eeae63f438661884f6ac19b035ea54f8d1ae5ff31a222e26dd8d1cb07.mp3", "archive_relative_path": "raw/audio/b5e/b5ea6c5eeae63f438661884f6ac19b035ea54f8d1ae5ff31a222e26dd8d1cb07.mp3" } ] } ], "prediction": "Ta'pe'l, we'gwi'jig na ugjit.", "reference": "Ta'pit, na negm nata'wisugwateget." }, { "id": "mic-sent-7c80bce866258f8639478586:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Eunice is driving around with her sweetheart.", "output_text": "Tio'tis alteja'lugwejig ugplgoqoml.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Eunice is driving around with her sweetheart.", "mic_Latn": "Tio'tis alteja'lugwejig ugplgoqoml." }, "canonical_ref": "entries/u/ugplgoqoml/ugplgoqoml.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dd9033702492ed844ce1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugplgoqoml/ugplgoqoml.html", "entry_url": "https://mikmaqonline.org/entries/u/ugplgoqoml/ugplgoqoml.html", "headword": "ugplgoqoml", "example_index": 0, "raw_html_path": "raw/entries/a92f001f4f2d561a796f63bd1545f7457a5b2ac38250cec305909b4fc23caac5.html", "raw_html_sha256": "aa14aec3efc94814a166e01ebfeb0e2b51470900c1a443897704a6825cc154f8", "fetched_at": "2026-07-12T02:46:13.605Z", "recordings": [ { "recording_id": "6b2a249a99f2de7b7ca6b06356add7735389ccd0aa2a776e365527f1dd92ab5c", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b8b/b8b0b42ce85074113fe9332f3986f855b23e6dddf18f7f6c7f8b255a08d61b20.mp3", "archive_relative_path": "raw/audio/b8b/b8b0b42ce85074113fe9332f3986f855b23e6dddf18f7f6c7f8b255a08d61b20.mp3" } ] } ], "prediction": "E'nise'g etlmisga'latl ugjitl.", "reference": "Tio'tis alteja'lugwejig ugplgoqoml." }, { "id": "mic-sent-7c9f1e0c0017bc677de97e96:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Joseph is shy about asking a young woman to go out.", "output_text": "So'sep naqatgelsit pipaniman e'pite'sl tua'tinew.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Joseph is shy about asking a young woman to go out.", "mic_Latn": "So'sep naqatgelsit pipaniman e'pite'sl tua'tinew." }, "canonical_ref": "entries/n/naqatgelsit/naqatgelsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b1f8274f525f0f61cc62", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/naqatgelsit/naqatgelsit.html", "entry_url": "https://mikmaqonline.org/entries/n/naqatgelsit/naqatgelsit.html", "headword": "naqatgelsit", "example_index": 0, "raw_html_path": "raw/entries/012a1056852b1f2babc732332bd801b28024bee08f0fbc45bbb8d2b49aa8c386.html", "raw_html_sha256": "0a9d09fce58fc4e1e3196124289de7f04a8012debf800602961e9bb0f00e84ae", "fetched_at": "2026-07-12T02:42:04.123Z", "recordings": [ { "recording_id": "c33c9aec004eb1514e1f8d806f641ebf69afbdef35e1556e4dfcf974a82ea2e8", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5d8/5d810d8e1e01bf5fcd27e4e0ac6f8221dab808f8e7c4e062483a704631ca2e3c.mp3", "archive_relative_path": "raw/audio/5d8/5d810d8e1e01bf5fcd27e4e0ac6f8221dab808f8e7c4e062483a704631ca2e3c.mp3" } ] } ], "prediction": "So'sep gesatg ta'n tujiw gisgugwet.", "reference": "So'sep naqatgelsit pipaniman e'pite'sl tua'tinew." }, { "id": "mic-sent-7cb9fdde0a6c426702cf8312:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who's giving away these hats?", "output_text": "Wen ignmuetoqol ula a'gusnn?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who's giving away these hats?", "mic_Latn": "Wen ignmuetoqol ula a'gusnn?" }, "canonical_ref": "entries/i/ignmuetoq/ignmuetoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-36b6e9394e2a266a1af1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/ignmuetoq/ignmuetoq.html", "entry_url": "https://mikmaqonline.org/entries/i/ignmuetoq/ignmuetoq.html", "headword": "ignmuetoq", "example_index": 0, "raw_html_path": "raw/entries/10c38315803ac77432c517b9f157b42aeb90b3e1323279cfd1a75d3c3b3aba99.html", "raw_html_sha256": "e03083c44aa300e563d4e94813a13ab75715d0e16e690ddbe0a13b801422f84a", "fetched_at": "2026-07-12T02:40:05.502Z", "recordings": [ { "recording_id": "a91017a0e3f6ff1f2004a054aa73fb50ef70acb102ff2f6f66c87b93d2e9204c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/50a/50af7124bf094100b4762d974509f8721de39a68345ffa5e8e8f7d4077c8189a.mp3", "archive_relative_path": "raw/audio/50a/50af7124bf094100b4762d974509f8721de39a68345ffa5e8e8f7d4077c8189a.mp3" } ] } ], "prediction": "Wen na'te'l ula gmu'ji'j?", "reference": "Wen ignmuetoqol ula a'gusnn?" }, { "id": "mic-sent-7cc094561d2e40ce44a103d1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The spider is crawling down inside the watercan.", "output_text": "Go'gwejij pemnisapegit samqwano'qigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The spider is crawling down inside the watercan.", "mic_Latn": "Go'gwejij pemnisapegit samqwano'qigtug." }, "canonical_ref": "entries/n/nisapegit/nisapegit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0a9997e310be7a52b49c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nisapegit/nisapegit.html", "entry_url": "https://mikmaqonline.org/entries/n/nisapegit/nisapegit.html", "headword": "nisapegit", "example_index": 0, "raw_html_path": "raw/entries/aba5f0c80eaff90424d3f7856d90f0cddf9098536a9d59a7efdf72fe8447cc30.html", "raw_html_sha256": "1898ef06804e34316a3e55480ad353a2d11d71b438c3177f8183d655cb68c1f8", "fetched_at": "2026-07-12T02:42:35.929Z", "recordings": [ { "recording_id": "c2ee7f9f3b2acb16bc192e148cd5b5158b0df55a75c2aee191db32e5d0d954c5", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e69/e699e5af39ca51bcfba5273939b430d7d9507545060bbfd23bef80eb5e931328.mp3", "archive_relative_path": "raw/audio/e69/e699e5af39ca51bcfba5273939b430d7d9507545060bbfd23bef80eb5e931328.mp3" } ] } ], "prediction": "Nmu'ji'j etlmesg'p'tijigtug e'w'gwi'jig.", "reference": "Go'gwejij pemnisapegit samqwano'qigtug." }, { "id": "mic-sent-7df7013a62063b86c431e24c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What did you bump into?", "output_text": "Goqwei migutesg'mu's'p?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What did you bump into?", "mic_Latn": "Goqwei migutesg'mu's'p?" }, "canonical_ref": "entries/m/migutesg'g/migutesg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-370a27a73ea1eafb8304", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/migutesg'g/migutesg'g.html", "entry_url": "https://mikmaqonline.org/entries/m/migutesg'g/migutesg'g.html", "headword": "migutesg'g", "example_index": 0, "raw_html_path": "raw/entries/284570275090190917ebb843d1f38c60fb82704786c2216efe948540d6682bdb.html", "raw_html_sha256": "399adb2173616415acf0bf9c2f3cfada813f7b4930b9524e88b1fc6f1f9acef6", "fetched_at": "2026-07-12T02:41:34.044Z", "recordings": [ { "recording_id": "1f9477df16422ab103089f38097efb53ed68ba29fed0688de0990541998caed1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3d3/3d3be6fcea70e298641a181ea142857d9e895215d0a2b4535ca976fc16f772d2.mp3", "archive_relative_path": "raw/audio/3d3/3d3be6fcea70e298641a181ea142857d9e895215d0a2b4535ca976fc16f772d2.mp3" } ] } ], "prediction": "Goqwei etlmisga'tu'n?", "reference": "Goqwei migutesg'mu's'p?" }, { "id": "mic-sent-7ec6f7926f44f8805a363ab7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary likes to use arithmetic where she works.", "output_text": "Mali gesatg e'w'g mawgiljaqan ta'n etllugwej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary likes to use arithmetic where she works.", "mic_Latn": "Mali gesatg e'w'g mawgiljaqan ta'n etllugwej." }, "canonical_ref": "entries/m/mawgiljaqan/mawgiljaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0833b8b17b30296e6331", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mawgiljaqan/mawgiljaqan.html", "entry_url": "https://mikmaqonline.org/entries/m/mawgiljaqan/mawgiljaqan.html", "headword": "mawgiljaqan", "example_index": 0, "raw_html_path": "raw/entries/79328484c0d180aef24b105da381ec85379f725e69e0081b208fcddfb8988396.html", "raw_html_sha256": "09f9de8cbfcd9f1fa4947885286a0056d89eabd5cc68ef7bb8a3b180863a0c6a", "fetched_at": "2026-07-12T02:40:59.303Z", "recordings": [ { "recording_id": "f1039d086a539d40b2b097e74aff37f5752bc13f74bde9f8ceb42f17afb44b68", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/181/181105f032a98df7d93c769df9bbb8c6f9322cc48016288a8170ef9d9f26ca76.mp3", "archive_relative_path": "raw/audio/181/181105f032a98df7d93c769df9bbb8c6f9322cc48016288a8170ef9d9f26ca76.mp3" } ] } ], "prediction": "Mali ge's gesatg ta'n tujiw etlugowaqan.", "reference": "Mali gesatg e'w'g mawgiljaqan ta'n etllugwej." }, { "id": "mic-sent-7ec70b1c6beb3b545fc3c39b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Looks like my buddy laid down to sleep.", "output_text": "Nepasma'sisnaq nitapo'q.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Looks like my buddy laid down to sleep.", "mic_Latn": "Nepasma'sisnaq nitapo'q." }, "canonical_ref": "entries/n/nepasma'sit/nepasma'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ff730b7178b025b8257d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nepasma'sit/nepasma'sit.html", "entry_url": "https://mikmaqonline.org/entries/n/nepasma'sit/nepasma'sit.html", "headword": "nepasma'sit", "example_index": 0, "raw_html_path": "raw/entries/5942d4a8e84c6ff07005030909784b0a82453d967c1df02510a94fb1c67672d9.html", "raw_html_sha256": "3e1270eb829126fb901593c484d25f45da5553f34952c7a22246917dd9a223a4", "fetched_at": "2026-07-12T02:36:14.783Z", "recordings": [ { "recording_id": "65a3d8386d2d844ee4c68f4d4a281396b8426fc16ba65a619bfa2decd76ceb0e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/38a/38a6c4a71505341db6227539037214b171feb8c68edc8fe09f0765e3b6de1f9c.mp3", "archive_relative_path": "raw/audio/38a/38a6c4a71505341db6227539037214b171feb8c68edc8fe09f0765e3b6de1f9c.mp3" } ] } ], "prediction": "Gi's nige' na nitap gesatg.", "reference": "Nepasma'sisnaq nitapo'q." }, { "id": "mic-sent-7fa37ecb05aa216704e6db45:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she gotten a lot of use out of that canoe, he/she uses it daily.", "output_text": "Me' gatu pegitapetg na gwitn, lpa te'sigisg'g e'w'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she gotten a lot of use out of that canoe, he/she uses it daily.", "mic_Latn": "Me' gatu pegitapetg na gwitn, lpa te'sigisg'g e'w'g." }, "canonical_ref": "entries/p/pegitapetg/pegitapetg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-15eb7491979af6cf4680", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pegitapetg/pegitapetg.html", "entry_url": "https://mikmaqonline.org/entries/p/pegitapetg/pegitapetg.html", "headword": "pegitapetg", "example_index": 0, "raw_html_path": "raw/entries/c13c26f84a2f272a15d91ae63ed7a98022e4a8ca731a3dbbdc7e34ab9abb8468.html", "raw_html_sha256": "459b9d2365d729abe196d97bc21306bd2f8136e041ebf99721299d1acd1b760a", "fetched_at": "2026-07-12T02:43:21.457Z", "recordings": [ { "recording_id": "f35952a12afb2b7aa6c62dd184deb521dcf2450683518422857d871f3c7a5b97", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/42c/42c0003109e97eeee967b682b1d7916357b4dc38dba349f04c4153c08c4c9d73.mp3", "archive_relative_path": "raw/audio/42c/42c0003109e97eeee967b682b1d7916357b4dc38dba349f04c4153c08c4c9d73.mp3" } ] } ], "prediction": "Pugwelg'g na gmu'j, te's'g te'sipu'g.", "reference": "Me' gatu pegitapetg na gwitn, lpa te'sigisg'g e'w'g." }, { "id": "mic-sent-8006106186cc4485d1cc968f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Many boards will be made from this tree.", "output_text": "Pugwelgig nasqo'plaq ugjietaq ula miti's.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Many boards will be made from this tree.", "mic_Latn": "Pugwelgig nasqo'plaq ugjietaq ula miti's." }, "canonical_ref": "entries/n/nasqo'plaw/nasqo'plaw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b1c3452363933285b968", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nasqo'plaw/nasqo'plaw.html", "entry_url": "https://mikmaqonline.org/entries/n/nasqo'plaw/nasqo'plaw.html", "headword": "nasqo'plaw", "example_index": 0, "raw_html_path": "raw/entries/0198f2c20176e68abaadf8d7f4be8d5b5f6dd3f64b92887533487f5ef34dd37e.html", "raw_html_sha256": "518c3a66731f76d02fd12dc7014ac35f65b67306b31a39e86573a0dfed621d05", "fetched_at": "2026-07-12T02:42:08.485Z", "recordings": [ { "recording_id": "cd2c6e507accae7577bbd5022ccf3098c26c1836c91e574a7048635ddacee776", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/502/502895da1fde9cc49ae5b8c68b417a59f081f33e55aa0f00d187cb9178945f43.mp3", "archive_relative_path": "raw/audio/502/502895da1fde9cc49ae5b8c68b417a59f081f33e55aa0f00d187cb9178945f43.mp3" } ] } ], "prediction": "Pugwelga'toq ugjit na ula miti'g.", "reference": "Pugwelgig nasqo'plaq ugjietaq ula miti's." }, { "id": "mic-sent-8029978181d68d4e4fd76425:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where could it be? I have already gone up and down the stairs twice looking for it and I haven't found it yet.", "output_text": "Etug tami eteg? Gi's ta'pu toqjua'i aq nisa'si algwilm, mnaq we'jitu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where could it be? I have already gone up and down the stairs twice looking for it and I haven't found it yet.", "mic_Latn": "Etug tami eteg? Gi's ta'pu toqjua'i aq nisa'si algwilm, mnaq we'jitu." }, "canonical_ref": "entries/t/toqjua't/toqjua't.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-47e319729b41f2addac8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/toqjua't/toqjua't.html", "entry_url": "https://mikmaqonline.org/entries/t/toqjua't/toqjua't.html", "headword": "toqjua't", "example_index": 0, "raw_html_path": "raw/entries/0c3411b228bd72b140b7de9a260d502bc80f2f41c3a3efd1b7c03ff7fcece5da.html", "raw_html_sha256": "8fd6319b2e1d6065ecaa7a8f57f01aef73d5cc7873ccbf6923f7eb1c2c7d7214", "fetched_at": "2026-07-12T02:46:01.847Z", "recordings": [ { "recording_id": "90da67809aff4354f840976dcbc0bcddc8e4a44f3340d4b3eaa406f8b3818b1d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9f1/9f19d64efc7e1b267cc9381ca2d5733f2e6276a153a0be14ba9c81b2cc2a1e7c.mp3", "archive_relative_path": "raw/audio/9f1/9f19d64efc7e1b267cc9381ca2d5733f2e6276a153a0be14ba9c81b2cc2a1e7c.mp3" } ] } ], "prediction": "Tami eteg? Gi's gi's gesgmnaq te'sipi's'g aq nige' mu nugu' nugute'n.", "reference": "Etug tami eteg? Gi's ta'pu toqjua'i aq nisa'si algwilm, mnaq we'jitu." }, { "id": "mic-sent-803b8399613001c960dbc853:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "One is most uncomfortable in the heat.", "output_text": "Maw jigajiemg na eptegigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "One is most uncomfortable in the heat.", "mic_Latn": "Maw jigajiemg na eptegigtug." }, "canonical_ref": "entries/j/jigajiet/jigajiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-68de44eaaaf2731cfa33", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jigajiet/jigajiet.html", "entry_url": "https://mikmaqonline.org/entries/j/jigajiet/jigajiet.html", "headword": "jigajiet", "example_index": 0, "raw_html_path": "raw/entries/ec025e246c2be84e1a19e0a271fed67f5dfb7c07bab3131c9e3c2ff46ce8ea77.html", "raw_html_sha256": "39cf1c05884da3fd338da20fedb21d257747f6c40a543302a66fd538dd42e393", "fetched_at": "2026-07-12T02:40:17.005Z", "recordings": [ { "recording_id": "5fb541d9871811256cf1aaf80993ce94d9977b352a5c7ace45137acba0274b0a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dd2/dd24167af229a34f0d2817a3befbcab73472b0ea35e64ef803fc5177a7de7380.mp3", "archive_relative_path": "raw/audio/dd2/dd24167af229a34f0d2817a3befbcab73472b0ea35e64ef803fc5177a7de7380.mp3" } ] } ], "prediction": "Na'te's'g na we'gwi'g ta'n tujiw.", "reference": "Maw jigajiemg na eptegigtug." }, { "id": "mic-sent-80c6612c9a8c4c02ec2c2c9e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The storm stops all outside work.", "output_text": "Mtugunoqt naqang gujmugwei lugowaqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The storm stops all outside work.", "mic_Latn": "Mtugunoqt naqang gujmugwei lugowaqan." }, "canonical_ref": "entries/n/naqang/naqang.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1b82241b19b1c8562edf", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/naqang/naqang.html", "entry_url": "https://mikmaqonline.org/entries/n/naqang/naqang.html", "headword": "naqang", "example_index": 0, "raw_html_path": "raw/entries/3e4851b3c7aa3542e2155e38480b9ccef4a6f03ee74dd2fad55844eb7ff4d064.html", "raw_html_sha256": "d946bb644d891114390098702fc73b62998436328f6b5df04334088970cd58c6", "fetched_at": "2026-07-12T02:42:02.834Z", "recordings": [ { "recording_id": "d5ac88f27bb59d44afa6f82fdd9c2dacaa144e25c05dcb9ae4b47deedd9dfcd2", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/db4/db4e22e3fa001c9ac5c93f6ff8d60b867843ba148773a10b10c714529e38d3f1.mp3", "archive_relative_path": "raw/audio/db4/db4e22e3fa001c9ac5c93f6ff8d60b867843ba148773a10b10c714529e38d3f1.mp3" } ] } ], "prediction": "Pugwelg'g ta'n tujiw alugowaqan.", "reference": "Mtugunoqt naqang gujmugwei lugowaqan." }, { "id": "mic-sent-80df191e7c714c23f21a211d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Let me tell you about the dream I dreamt last night.", "output_text": "Pe'l agnutmulnap pewitaqan ta'n wela'gwe'g pewituap.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Let me tell you about the dream I dreamt last night.", "mic_Latn": "Pe'l agnutmulnap pewitaqan ta'n wela'gwe'g pewituap." }, "canonical_ref": "entries/p/pewitaqan/pewitaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8eba0fb3e534b909c286", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pewitaqan/pewitaqan.html", "entry_url": "https://mikmaqonline.org/entries/p/pewitaqan/pewitaqan.html", "headword": "pewitaqan", "example_index": 0, "raw_html_path": "raw/entries/75751a6e6890bbfbffc00d5b586607026874a759d2ca80647318c0357e7fc563.html", "raw_html_sha256": "31bd33ab462e63581ef19ff2ac026688a1716a8c2000f7d22240e12c8a757b4f", "fetched_at": "2026-07-12T02:43:50.808Z", "recordings": [ { "recording_id": "b470aee060644bb0cb159d6f00582c0f346484c3aaa73b889ed812a6a6058915", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3fc/3fc7f08ca05f167dc0f3e9a38acc0e75062d491c4e2070a1564ad2de45ba4cc6.mp3", "archive_relative_path": "raw/audio/3fc/3fc7f08ca05f167dc0f3e9a38acc0e75062d491c4e2070a1564ad2de45ba4cc6.mp3" } ] } ], "prediction": "Ge' nuta'latl miti'l wela'gwe'g.", "reference": "Pe'l agnutmulnap pewitaqan ta'n wela'gwe'g pewituap." }, { "id": "mic-sent-8121532e3cc9f5cc4877daea:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Diane has excellent eyesight, she notices everything.", "output_text": "Taie'n na mawne'talqigwat, nemitoq ms't goqwei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Diane has excellent eyesight, she notices everything.", "mic_Latn": "Taie'n na mawne'talqigwat, nemitoq ms't goqwei." }, "canonical_ref": "entries/n/ne'talqigwat/ne'talqigwat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e94213fc0cdb9ec6ae09", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ne'talqigwat/ne'talqigwat.html", "entry_url": "https://mikmaqonline.org/entries/n/ne'talqigwat/ne'talqigwat.html", "headword": "ne'talqigwat", "example_index": 0, "raw_html_path": "raw/entries/301007a624c63788f5bcd5ad67de6cdb22dc794d9afa80c6a66797bfd2e7979b.html", "raw_html_sha256": "e1267202923fdd091ea0fe7de297c0bc13293d2e2db10e349bc1695d3c0cf6bf", "fetched_at": "2026-07-12T02:42:24.656Z", "recordings": [ { "recording_id": "c1c1e2cc26938cfbabecf2bfa00d13a9b39dc23cb894c61d57b8b04a5dcaec36", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4d8/4d885ac8ec5fde4da5765c95d7d0824c5e845a0fc05073219419fdcf931eb3b0.mp3", "archive_relative_path": "raw/audio/4d8/4d885ac8ec5fde4da5765c95d7d0824c5e845a0fc05073219419fdcf931eb3b0.mp3" } ] } ], "prediction": "Diane na we'gwi'g, te's'g ta'n te'siw.", "reference": "Taie'n na mawne'talqigwat, nemitoq ms't goqwei." }, { "id": "mic-sent-813d8a13dc6c64e4ae59947f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "John is the one who is a cheater.", "output_text": "Sa'n na nujisespo'teget.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "John is the one who is a cheater.", "mic_Latn": "Sa'n na nujisespo'teget." }, "canonical_ref": "entries/s/sespo'teget/sespo'teget.html#example-2", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0565d3648a7cf973dab0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sespo'teget/sespo'teget.html", "entry_url": "https://mikmaqonline.org/entries/s/sespo'teget/sespo'teget.html", "headword": "sespo'teget", "example_index": 2, "raw_html_path": "raw/entries/1d7e01b88287a56bf8f513e556eaaf16c290f78218fa6125689279f20a451d0b.html", "raw_html_sha256": "90da0262fc08e5d80009b5fbe5783ef94fc58c400da7d0bdecda0481836eecb5", "fetched_at": "2026-07-12T02:44:53.830Z", "recordings": [ { "recording_id": "fab63c6e7e976760be7fd457d933366f3c8cf3bdff7fa6889475fbc19c5116b1", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bf7/bf7ac7e406202a641fee439b1cfb137494461f655f212988454a700fc2fd9f96.mp3", "archive_relative_path": "raw/audio/bf7/bf7ac7e406202a641fee439b1cfb137494461f655f212988454a700fc2fd9f96.mp3" } ] } ], "prediction": "Sa'n na we'gwi'g.", "reference": "Sa'n na nujisespo'teget." }, { "id": "mic-sent-821475446090266c65b8440f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There are those who are woman chasers.", "output_text": "Eimu'tijig na e'pitewe'smg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There are those who are woman chasers.", "mic_Latn": "Eimu'tijig na e'pitewe'smg." }, "canonical_ref": "entries/e/e'pitewe'sm/e'pitewe'sm.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ab31b3e745c141123b47", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/e'pitewe'sm/e'pitewe'sm.html", "entry_url": "https://mikmaqonline.org/entries/e/e'pitewe'sm/e'pitewe'sm.html", "headword": "e'pitewe'sm", "example_index": 0, "raw_html_path": "raw/entries/9d220a9cbb7bf1fb251e7cb84dc8eaf1b1d66fce9cc515728b8f184d97cf00ee.html", "raw_html_sha256": "bdf067ab615b29196c32a71fc88b90ac0611048c9d78fa626db06738e2d4376a", "fetched_at": "2026-07-12T02:38:09.326Z", "recordings": [ { "recording_id": "298a19efae5dc499bd64fbe41df25125ec5f52ebfd477ea35fa377304f5f097e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/546/5469917d1a8d1b3d94e109ce851ca0fc8fe2f6ecad21d5ef4007b7e95135d9b3.mp3", "archive_relative_path": "raw/audio/546/5469917d1a8d1b3d94e109ce851ca0fc8fe2f6ecad21d5ef4007b7e95135d9b3.mp3" } ] } ], "prediction": "Ala ta'n te's'g na wi'gwi'g.", "reference": "Eimu'tijig na e'pitewe'smg." }, { "id": "mic-sent-8264c86328e40b7b955bba55:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's so cold the windows are all frosted up.", "output_text": "Tewjitge'g lpa tuop'ti'l wastewt'gl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's so cold the windows are all frosted up.", "mic_Latn": "Tewjitge'g lpa tuop'ti'l wastewt'gl." }, "canonical_ref": "entries/w/wastewt'g/wastewt'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c574a45d9dcea2f36897", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wastewt'g/wastewt'g.html", "entry_url": "https://mikmaqonline.org/entries/w/wastewt'g/wastewt'g.html", "headword": "wastewt'g", "example_index": 0, "raw_html_path": "raw/entries/3e7f2916f05ac32bc50bf48aabc6a824f1a796487faf3de2e9834118249b29fe.html", "raw_html_sha256": "9921259ba13f1cc60cc86e0dc73dcff02af731e7c79d0018fc72947f2e66f48b", "fetched_at": "2026-07-12T02:46:43.657Z", "recordings": [ { "recording_id": "4d29b2b5f82291cbcc1f5f04ea16116429ce81ccbdc93c06c53993a56875c278", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/212/212b6d4704f0f786569d6924f3efab2d2da46d5bc258fea813bff0bd839ef8cb.mp3", "archive_relative_path": "raw/audio/212/212b6d4704f0f786569d6924f3efab2d2da46d5bc258fea813bff0bd839ef8cb.mp3" } ] } ], "prediction": "Tetuji'jg na lpa'tu'n tujiw gesgm'g.", "reference": "Tewjitge'g lpa tuop'ti'l wastewt'gl." }, { "id": "mic-sent-82c32a1dd17a1455f2a28da5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You have to write it all down.", "output_text": "Amujpa ms't ewi'g'mn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You have to write it all down.", "mic_Latn": "Amujpa ms't ewi'g'mn." }, "canonical_ref": "entries/e/ewi'g'g/ewi'g'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d195f9b205a15f6a4787", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/ewi'g'g/ewi'g'g.html", "entry_url": "https://mikmaqonline.org/entries/e/ewi'g'g/ewi'g'g.html", "headword": "ewi'g'g", "example_index": 0, "raw_html_path": "raw/entries/0e40ff3be47fda772923d81274115c6fb65e4a47e0cae61fddb2704dee59e9f3.html", "raw_html_sha256": "6d683174313eba77e6ba32039ab3ccff5dec41efe49c57c1bc3cd98cdb159e18", "fetched_at": "2026-07-12T02:38:29.330Z", "recordings": [ { "recording_id": "dc7b3d33076990845c19dbaa9dc075f7bd30d9379f711271b2d6e4047adab7fa", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4fe/4fe85d16b4896dc1bbfcbeb936c62136280b6f5457d059ebda5bd7a7959613bd.mp3", "archive_relative_path": "raw/audio/4fe/4fe85d16b4896dc1bbfcbeb936c62136280b6f5457d059ebda5bd7a7959613bd.mp3" } ] } ], "prediction": "Amujpa ms't goqwei teliaq.", "reference": "Amujpa ms't ewi'g'mn." }, { "id": "mic-sent-82dde7210b6c4dc02a7b7439:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "His/her/it's intestines are in his/her/it's stomach.", "output_text": "Ul'gsi'l etegl ugtlaminug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "His/her/it's intestines are in his/her/it's stomach.", "mic_Latn": "Ul'gsi'l etegl ugtlaminug." }, "canonical_ref": "entries/u/uligsi/uligsi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ec7e85e1824256f05e44", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/uligsi/uligsi.html", "entry_url": "https://mikmaqonline.org/entries/u/uligsi/uligsi.html", "headword": "uligsi", "example_index": 0, "raw_html_path": "raw/entries/6cf2f9db527c7c5f83f55244bbb8370108be00a0af6caba2fa75ef7d3bf96b67.html", "raw_html_sha256": "6628f08df70a847d36e3918cc33547176b73fb4898df7ee178e05bf9728c4f92", "fetched_at": "2026-07-12T02:46:22.649Z", "recordings": [ { "recording_id": "cae4d1e60cf70710faff05f6b8e447965f083e7066593abff09b4250cb05175c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e8c/e8cbf4ffdc8f4c3aa2bff341f72e105b42450360c2053d36f08fe9e4cbd21c56.mp3", "archive_relative_path": "raw/audio/e8c/e8cbf4ffdc8f4c3aa2bff341f72e105b42450360c2053d36f08fe9e4cbd21c56.mp3" } ] } ], "prediction": "Amujpa ugtaqanigtug ugjit.", "reference": "Ul'gsi'l etegl ugtlaminug." }, { "id": "mic-sent-82f7f724cc914f95544d79e9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I'm happy he/she has a clean tail, I was afraid his/her tail would be full of burdocks.", "output_text": "Welta'si waqamaluat, jipatmap ugsuguni ugju'wan gesaluejijig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I'm happy he/she has a clean tail, I was afraid his/her tail would be full of burdocks.", "mic_Latn": "Welta'si waqamaluat, jipatmap ugsuguni ugju'wan gesaluejijig." }, "canonical_ref": "entries/w/waqamaluat/waqamaluat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-99bebcb5c8d423dc0052", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waqamaluat/waqamaluat.html", "entry_url": "https://mikmaqonline.org/entries/w/waqamaluat/waqamaluat.html", "headword": "waqamaluat", "example_index": 0, "raw_html_path": "raw/entries/13af7f8b7c0025860f15351c31d1718da2775d331849635ad09d56e4860e15d8.html", "raw_html_sha256": "c4b38b7b93bcac751de804f7479393c0f166356d9537a45ed14af0e897f6a0af", "fetched_at": "2026-07-12T02:46:36.631Z", "recordings": [ { "recording_id": "d52a89b6751a86c982286af20255d9bf9dd1d459047e59e1068afcec1418528a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5c2/5c2a42bae9cee00f5ed686d203a26c2c1915db001a60f6fe0333211ae7f76156.mp3", "archive_relative_path": "raw/audio/5c2/5c2a42bae9cee00f5ed686d203a26c2c1915db001a60f6fe0333211ae7f76156.mp3" } ] } ], "prediction": "Lpa we'gwi'g, tlia's'g ta'n tujiw gmu'ji'j.", "reference": "Welta'si waqamaluat, jipatmap ugsuguni ugju'wan gesaluejijig." }, { "id": "mic-sent-83237911d99bc6004ff2719e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "She/he has just arrived.", "output_text": "Atel nige' pegising.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "She/he has just arrived.", "mic_Latn": "Atel nige' pegising." }, "canonical_ref": "entries/a/atel/atel.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3f184a96109d17c0bb99", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/atel/atel.html", "entry_url": "https://mikmaqonline.org/entries/a/atel/atel.html", "headword": "atel", "example_index": 0, "raw_html_path": "raw/entries/07ab96f852182e96fe7c5e82c200bc10ee7b2affade8bf515939247d42c63bc2.html", "raw_html_sha256": "ab291edc304b0906a80fc4d0187e82a186b9dc9e30bbb9417c2e1923267a3243", "fetched_at": "2026-07-12T02:37:24.245Z", "recordings": [ { "recording_id": "d739b0d1477fd8e8d4a39a09de06aa8d6a0120afd70047164e127e10906312bd", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6e8/6e852d785dfe6a995b7d14d8f328154b2f211a247d124361eab3b1d1c9b995fb.mp3", "archive_relative_path": "raw/audio/6e8/6e852d785dfe6a995b7d14d8f328154b2f211a247d124361eab3b1d1c9b995fb.mp3" } ] } ], "prediction": "Pugwelg pas'g.", "reference": "Atel nige' pegising." }, { "id": "mic-sent-83e9055f4e2c4f5d1b6c04c3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mutton tastes very good.", "output_text": "Jijgluewjuwei maw wigapu'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mutton tastes very good.", "mic_Latn": "Jijgluewjuwei maw wigapu'g." }, "canonical_ref": "entries/j/jijgluewj/jijgluewj.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-fd9e349dace9ebcc2f26", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jijgluewj/jijgluewj.html", "entry_url": "https://mikmaqonline.org/entries/j/jijgluewj/jijgluewj.html", "headword": "jijgluewj", "example_index": 0, "raw_html_path": "raw/entries/f49b88a7b610fa0e32d49849d46035843c8025cfc479f104f34d32b177ec013f.html", "raw_html_sha256": "8add35d641da513d22a70ed834da94ac63db9534da1bef96e0ebb7cab5c48d5e", "fetched_at": "2026-07-12T02:40:19.622Z", "recordings": [ { "recording_id": "84fdfbcdfb93c8b059a544ea801b32f0b8a898a7332ea4fc4642540368e1264e", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a63/a637bc9af7316f9cd5e52f81984c20d1abfda78af2b36c672fcad7867c53c53e.mp3", "archive_relative_path": "raw/audio/a63/a637bc9af7316f9cd5e52f81984c20d1abfda78af2b36c672fcad7867c53c53e.mp3" } ] } ], "prediction": "Pugwelg na we'gwig.", "reference": "Jijgluewjuwei maw wigapu'g." }, { "id": "mic-sent-84677e04eff6ee4bc270dbfa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I help my son to change the writing on the paper.", "output_text": "Ngwis apoqonmaq sa'se'wi'g'g wi'gatign.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I help my son to change the writing on the paper.", "mic_Latn": "Ngwis apoqonmaq sa'se'wi'g'g wi'gatign." }, "canonical_ref": "entries/s/sa'se'wi'g'g/sa'se'wi'g'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-afc21e09ad447506a270", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sa'se'wi'g'g/sa'se'wi'g'g.html", "entry_url": "https://mikmaqonline.org/entries/s/sa'se'wi'g'g/sa'se'wi'g'g.html", "headword": "sa'se'wi'g'g", "example_index": 0, "raw_html_path": "raw/entries/f6a5f5290e2fe533b0087cb416a296ac98a8fda1a5350ff5ac40fce3f0a2f08f.html", "raw_html_sha256": "92fda0169d5ae16a4f2b78db4a30c53fd3f1fd46192cad6fe4d7e08cbaeb4ca8", "fetched_at": "2026-07-12T02:44:44.969Z", "recordings": [ { "recording_id": "ea19a1d5b204ea663a8270010104cc68dd91d88dd4e52820f0e0cde6df8af077", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b15/b15c14adc0d2d144315694dfb23d174a474ebbf62e4b73f68eae7ad3ed8f322b.mp3", "archive_relative_path": "raw/audio/b15/b15c14adc0d2d144315694dfb23d174a474ebbf62e4b73f68eae7ad3ed8f322b.mp3" } ] } ], "prediction": "Nugu' nugu' nuji'j etlugowa'toq wi'gatignigtug.", "reference": "Ngwis apoqonmaq sa'se'wi'g'g wi'gatign." }, { "id": "mic-sent-84fb231d30672fd6d217668a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "William cuts the meat into small pieces.", "output_text": "Sulian aps'sg wi'us.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "William cuts the meat into small pieces.", "mic_Latn": "Sulian aps'sg wi'us." }, "canonical_ref": "entries/a/aps'sg/aps'sg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-52a25bbcdb741fdb563e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/aps'sg/aps'sg.html", "entry_url": "https://mikmaqonline.org/entries/a/aps'sg/aps'sg.html", "headword": "aps'sg", "example_index": 0, "raw_html_path": "raw/entries/73597a840c6b079b3293f94b4427b3db44a64a577a6f93cbf75f819b4cda9473.html", "raw_html_sha256": "49a02a4cb05c1b11d9bed6bc64e821f9936997df5f5df75de633579ae65b92e0", "fetched_at": "2026-07-12T02:37:11.139Z", "recordings": [ { "recording_id": "2436d3db36f07e79ba35b9f73f14886ed8a8de11ba8ff6f5f182fcf2ef7a4442", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/61a/61a9154ed50dc8fc9e0cdc47de0e4cd1ad127e07f152025691e39c6df79f0a26.mp3", "archive_relative_path": "raw/audio/61a/61a9154ed50dc8fc9e0cdc47de0e4cd1ad127e07f152025691e39c6df79f0a26.mp3" } ] } ], "prediction": "So'lia's gesatg na wi'g.", "reference": "Sulian aps'sg wi'us." }, { "id": "mic-sent-863e1c73ef257c547bf4740d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I boiled my pot dry again!", "output_text": "Gis ap niwoqsitaq ntuwomaq!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I boiled my pot dry again!", "mic_Latn": "Gis ap niwoqsitaq ntuwomaq!" }, "canonical_ref": "entries/n/niwoqsit/niwoqsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-82c609bd0a8016f1d1d7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/niwoqsit/niwoqsit.html", "entry_url": "https://mikmaqonline.org/entries/n/niwoqsit/niwoqsit.html", "headword": "niwoqsit", "example_index": 0, "raw_html_path": "raw/entries/2377727b745d9f501484a4a6412779b246b6789a39548a07ff21176af8d03356.html", "raw_html_sha256": "71f2823e554b7ad549a80585959d9818ce99a8687840a8e773f5a74c12ce195a", "fetched_at": "2026-07-12T02:42:39.843Z", "recordings": [ { "recording_id": "f1acd22c441d63a50b988f6447333f19fff64a21b7c3025dc20af73430707dfe", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3d4/3d4b81b8ebf898c765dd951bc2a308ceb2b8a4ee520ae0694c9764639f4657d6.mp3", "archive_relative_path": "raw/audio/3d4/3d4b81b8ebf898c765dd951bc2a308ceb2b8a4ee520ae0694c9764639f4657d6.mp3" } ] } ], "prediction": "Gi's nige' gisga'toq ntmu'n!", "reference": "Gis ap niwoqsitaq ntuwomaq!" }, { "id": "mic-sent-86a28b427734b3d582cce083:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she keeps stepping outside to smoke.", "output_text": "Gujmug i'tu'puguwait aq wetmat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she keeps stepping outside to smoke.", "mic_Latn": "Gujmug i'tu'puguwait aq wetmat." }, "canonical_ref": "entries/w/wetmat/wetmat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dd7a06a1583fcfa85a49", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wetmat/wetmat.html", "entry_url": "https://mikmaqonline.org/entries/w/wetmat/wetmat.html", "headword": "wetmat", "example_index": 0, "raw_html_path": "raw/entries/82ecce5da01ee0217b10911a6e1870918b9072217fd8239bf38bf702b4ac7059.html", "raw_html_sha256": "ec622f4be9376c5b3db84991f2a3d5bc8307f024c60ab5fd19d9a7a40303bb73", "fetched_at": "2026-07-12T02:47:24.298Z", "recordings": [ { "recording_id": "a8cf1a2355509221f3f58248a4fed9e6008d034f082c29e43a81498c3ba4f59a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/343/3439ee333558118b81f04bc56f201d369fe91005306f8d20f0182fe23d5afe62.mp3", "archive_relative_path": "raw/audio/343/3439ee333558118b81f04bc56f201d369fe91005306f8d20f0182fe23d5afe62.mp3" } ] } ], "prediction": "Te'sipo'toq na'te's'g ugjit.", "reference": "Gujmug i'tu'puguwait aq wetmat." }, { "id": "mic-sent-86b6f981beb655aed3668416:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This man has a broad back.", "output_text": "Ula ji'nm mawgesgiaqasit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This man has a broad back.", "mic_Latn": "Ula ji'nm mawgesgiaqasit." }, "canonical_ref": "entries/g/gesgiaqasit/gesgiaqasit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f00386f8d4b5429eaa3c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesgiaqasit/gesgiaqasit.html", "entry_url": "https://mikmaqonline.org/entries/g/gesgiaqasit/gesgiaqasit.html", "headword": "gesgiaqasit", "example_index": 0, "raw_html_path": "raw/entries/11aeeeb99c1170876d8b8be573f61f9ccab9b0d888f1220b22a355b914c11a87.html", "raw_html_sha256": "84ca4ebe2653afb39281534be43cf7983eb5f246a729ea323dbd6ba4893fc96f", "fetched_at": "2026-07-12T02:39:05.606Z", "recordings": [ { "recording_id": "af3cb478a5a453004a5dfde11db876294a8e6d6da96f20e36095cc51053c2f3a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7f9/7f9f5a0cba66245b59d30db26b3aa51a4daa41f2999fb6d3608a1d56e88e7fa4.mp3", "archive_relative_path": "raw/audio/7f9/7f9f5a0cba66245b59d30db26b3aa51a4daa41f2999fb6d3608a1d56e88e7fa4.mp3" } ] } ], "prediction": "Ula ji'nm gesatg.", "reference": "Ula ji'nm mawgesgiaqasit." }, { "id": "mic-sent-871ec3f6164433718a4c2311:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary has taken a crooked picture of her cat.", "output_text": "Mali gisiistu'napui'gatl uggajuewjml.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary has taken a crooked picture of her cat.", "mic_Latn": "Mali gisiistu'napui'gatl uggajuewjml." }, "canonical_ref": "entries/i/istu'napui'gatl/istu'napui'gatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1576efc370519d407605", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/istu'napui'gatl/istu'napui'gatl.html", "entry_url": "https://mikmaqonline.org/entries/i/istu'napui'gatl/istu'napui'gatl.html", "headword": "istu'napui'gatl", "example_index": 0, "raw_html_path": "raw/entries/0384e4013c333d70fc00451e9c2ffedbf8a172312b6459033de8458674ceaccd.html", "raw_html_sha256": "32e0e740d2c8f6992422c6c9abd2ab82b3e0954b594bf2fff5a09c52e5bd96d8", "fetched_at": "2026-07-12T02:40:12.179Z", "recordings": [ { "recording_id": "8a2ff1fb3f9248540c5208139b8892afefdf2f2e02147f57a86493150ba10aae", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fd0/fd0ed6b02bac11fe92198c82ccfcf2a5a54040064130cff694cace167eb776c5.mp3", "archive_relative_path": "raw/audio/fd0/fd0ed6b02bac11fe92198c82ccfcf2a5a54040064130cff694cace167eb776c5.mp3" } ] } ], "prediction": "Mali gesatg ugjitl ugti'l.", "reference": "Mali gisiistu'napui'gatl uggajuewjml." }, { "id": "mic-sent-87b256a5c205f500de032b2f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she moves from the table and says I'm ready.", "output_text": "Sitapa'sit patawtigtug aq teluet gisgajei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she moves from the table and says I'm ready.", "mic_Latn": "Sitapa'sit patawtigtug aq teluet gisgajei." }, "canonical_ref": "entries/s/sitapa'sit/sitapa'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-39390a5f0492002e1c9f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sitapa'sit/sitapa'sit.html", "entry_url": "https://mikmaqonline.org/entries/s/sitapa'sit/sitapa'sit.html", "headword": "sitapa'sit", "example_index": 0, "raw_html_path": "raw/entries/4dad7d81811257c4b2459393ab18d32a9b1fd14f7961bc7cb73c864fcfdde876.html", "raw_html_sha256": "867b603339b726770aaf34fed41799ecab461f459596a14a89b8ab6ac4b16ae3", "fetched_at": "2026-07-12T02:36:10.152Z", "recordings": [ { "recording_id": "792bb28b7147203a92e61c308b2b812e6a3f2899b8a5829c6d765cdfdd22f7dd", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dde/ddebecaf5062272bc6132a8feacb19563f7ae4bcc0ea144b7d57a8bc5decfce1.mp3", "archive_relative_path": "raw/audio/dde/ddebecaf5062272bc6132a8feacb19563f7ae4bcc0ea144b7d57a8bc5decfce1.mp3" } ] } ], "prediction": "Ta'n tujiw ta'n te'sipow aq telte's'g.", "reference": "Sitapa'sit patawtigtug aq teluet gisgajei." }, { "id": "mic-sent-8855f2e55a86efc87fd62f34:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There are two of us steering and we don't know where we're going.", "output_text": "Tapusieg pema'gwi'tegeieg aq mu geitueg ta'n ela'tieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There are two of us steering and we don't know where we're going.", "mic_Latn": "Tapusieg pema'gwi'tegeieg aq mu geitueg ta'n ela'tieg." }, "canonical_ref": "entries/p/pema'gwi'teget/pema'gwi'teget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d1b8ee1f53b23f61eed2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pema'gwi'teget/pema'gwi'teget.html", "entry_url": "https://mikmaqonline.org/entries/p/pema'gwi'teget/pema'gwi'teget.html", "headword": "pema'gwi'teget", "example_index": 0, "raw_html_path": "raw/entries/c4b82959546d927036d968407042bd81f39862625b0b33e955a07ca5efaf92ce.html", "raw_html_sha256": "db383ee37bcd609f16ac73c65ffd7ad3ff1d1fba849a5f6e53f7a7888271ea40", "fetched_at": "2026-07-12T02:43:28.396Z", "recordings": [ { "recording_id": "7d4b53f45b06e150df45a37b35111da60d5fc5078156ce35ea3a5639067f380a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/62d/62d57b448478ed8a16f5a2652e8d088e0fff627db455e126f4dfcabce5f5baf2.mp3", "archive_relative_path": "raw/audio/62d/62d57b448478ed8a16f5a2652e8d088e0fff627db455e126f4dfcabce5f5baf2.mp3" } ] } ], "prediction": "Amujpa nige' na'te'g aq mu ge's goqwei ta'n tujiw.", "reference": "Tapusieg pema'gwi'tegeieg aq mu geitueg ta'n ela'tieg." }, { "id": "mic-sent-8862b95ab4fd26b645954afe:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she cuts through all the papers.", "output_text": "Lpa 'ms't saps'gl wi'gatignn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she cuts through all the papers.", "mic_Latn": "Lpa 'ms't saps'gl wi'gatignn." }, "canonical_ref": "entries/s/saps'g/saps'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-38829b80d8a08ce9f6df", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/saps'g/saps'g.html", "entry_url": "https://mikmaqonline.org/entries/s/saps'g/saps'g.html", "headword": "saps'g", "example_index": 0, "raw_html_path": "raw/entries/050b6425bf72d69e878452de8fdc90bf1e6544c65a7fc611619a9dc8a19a5bf3.html", "raw_html_sha256": "4797f5e5b1335c336f26b4ce07d0cd7023c8f729373bad8a6cb34184e1ea6476", "fetched_at": "2026-07-12T02:36:07.038Z", "recordings": [ { "recording_id": "0cf1df3ae728bfb1b11bfac577b32ca85d396f79dc11ab456a047f9cf42e5054", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c81/c81093dbe6164be30b53c84a07088cfe428901d07189d4965b142895e7252c70.mp3", "archive_relative_path": "raw/audio/c81/c81093dbe6164be30b53c84a07088cfe428901d07189d4965b142895e7252c70.mp3" } ] } ], "prediction": "Te's'g ta'n te'sijg nuji'jg.", "reference": "Lpa 'ms't saps'gl wi'gatignn." }, { "id": "mic-sent-8867eed58f83fe51425aae55:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "They say that Peter conserves his finances.", "output_text": "Teluejig Pie'l mawweso'tg ugsulieweim.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "They say that Peter conserves his finances.", "mic_Latn": "Teluejig Pie'l mawweso'tg ugsulieweim." }, "canonical_ref": "entries/w/weso'tg/weso'tg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-69be32f40978480ac4ee", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/weso'tg/weso'tg.html", "entry_url": "https://mikmaqonline.org/entries/w/weso'tg/weso'tg.html", "headword": "weso'tg", "example_index": 0, "raw_html_path": "raw/entries/59149b8626b390be423efbdf552152bb21d788f6cb5d273586c713b19904af72.html", "raw_html_sha256": "e6ebdec81047b5e5d61124248a0c48275bfa74d74409c3e16f6c0232235f1398", "fetched_at": "2026-07-12T02:47:20.156Z", "recordings": [ { "recording_id": "f8319e7c65e4164750a1a873a4cd204d36ceb79dad33ecc54207fee89da73091", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8cb/8cbafa7b6b6343f72a73a11ae267722f24776eb97d4b8ea8d039332aafa79881.mp3", "archive_relative_path": "raw/audio/8cb/8cbafa7b6b6343f72a73a11ae267722f24776eb97d4b8ea8d039332aafa79881.mp3" } ] } ], "prediction": "Teluejig Pie'l ugjit ugjit.", "reference": "Teluejig Pie'l mawweso'tg ugsulieweim." }, { "id": "mic-sent-890a70bcf8d999340a0a5bc9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This newborn has lots of hair.", "output_text": "Me' gatu ula qopisun mamuiusapunit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This newborn has lots of hair.", "mic_Latn": "Me' gatu ula qopisun mamuiusapunit." }, "canonical_ref": "entries/u/usapunit/usapunit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b7cf9a1f4178fc057910", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/usapunit/usapunit.html", "entry_url": "https://mikmaqonline.org/entries/u/usapunit/usapunit.html", "headword": "usapunit", "example_index": 0, "raw_html_path": "raw/entries/24df84db00e3e890f8826da6aff3c8cdef46a763a875c2d2c5d734cea14cf52b.html", "raw_html_sha256": "abe38e62f8a479eaf5d701b2405c2dd96b487f02798a46aab0235fb86e0d2d6f", "fetched_at": "2026-07-12T02:46:26.764Z", "recordings": [ { "recording_id": "e237940d572f08ff090fa28137f2ba17a39152be9153ad04ab34886aac413df9", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/543/543dbf6a3f6e96badb8b1d6dcde8deaabe0732cd8e7147d9a78cbf27979ff8eb.mp3", "archive_relative_path": "raw/audio/543/543dbf6a3f6e96badb8b1d6dcde8deaabe0732cd8e7147d9a78cbf27979ff8eb.mp3" } ] } ], "prediction": "We'gwi'jig na ula pilei.", "reference": "Me' gatu ula qopisun mamuiusapunit." }, { "id": "mic-sent-89386b199e825d8bf0a538e1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "S\\he shakes his\\her bottle before s\\he takes a drink.", "output_text": "Je tmg pepuegetl ugpu'taiml gesgmnaq esamqwagw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "S\\he shakes his\\her bottle before s\\he takes a drink.", "mic_Latn": "Je tmg pepuegetl ugpu'taiml gesgmnaq esamqwagw." }, "canonical_ref": "entries/p/pepuegetl/pepuegetl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-706e7dcbda7144e1d757", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pepuegetl/pepuegetl.html", "entry_url": "https://mikmaqonline.org/entries/p/pepuegetl/pepuegetl.html", "headword": "pepuegetl", "example_index": 0, "raw_html_path": "raw/entries/50d0fddc36ceaa42003657b1f7abd44f77824caa04e88b8c6d9d7e39db72111b.html", "raw_html_sha256": "e5e1c8f81927bdaf48a2918fb8bb37a8838b5601a89e1724bce635c1cacefbe9", "fetched_at": "2026-07-12T02:43:40.048Z", "recordings": [ { "recording_id": "56166fb3e5abaa0edc84c4d2686720078c489e89a20c67c11a79b7755633d594", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/50d/50d16d1301f2a1484e7dc6375457c35380f309cd4d6e63db478fb9b1ba19eae8.mp3", "archive_relative_path": "raw/audio/50d/50d16d1301f2a1484e7dc6375457c35380f309cd4d6e63db478fb9b1ba19eae8.mp3" } ] } ], "prediction": "Gesatg ugta'latl gesgmnaq gesgmatl.", "reference": "Je tmg pepuegetl ugpu'taiml gesgmnaq esamqwagw." }, { "id": "mic-sent-8938dd88f451b8da491e69e9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The rocking chair is rocking in the wind.", "output_text": "Lalamiaqawei ugju'snigtug etllalamo'qiaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The rocking chair is rocking in the wind.", "mic_Latn": "Lalamiaqawei ugju'snigtug etllalamo'qiaq." }, "canonical_ref": "entries/n/nanamo'qiaq/nanamo'qiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8aa185301f204764f76d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nanamo'qiaq/nanamo'qiaq.html", "entry_url": "https://mikmaqonline.org/entries/n/nanamo'qiaq/nanamo'qiaq.html", "headword": "nanamo'qiaq", "example_index": 0, "raw_html_path": "raw/entries/258348dd94166531f70f812ea27571bb2898e3faca12c86a09a40ae52bc2a0f6.html", "raw_html_sha256": "006e98e511eda9be7733817152a23e7e0d12a61c15c4d5a639b22b24d7d5ad4b", "fetched_at": "2026-07-12T02:41:57.882Z", "recordings": [ { "recording_id": "0ef701c5bf34565594daa1377abf8b0e4511ee9658eeba55de0be8ca473f9684", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/63f/63f25101735a9f7fb2b429a3150e9f85e83ead3a4f1b4e79db866864e3a13f0c.mp3", "archive_relative_path": "raw/audio/63f/63f25101735a9f7fb2b429a3150e9f85e83ead3a4f1b4e79db866864e3a13f0c.mp3" } ] } ], "prediction": "Lpa wi'gwi'g na wi'gwigtug.", "reference": "Lalamiaqawei ugju'snigtug etllalamo'qiaq." }, { "id": "mic-sent-89fda9f232ebdaf11faf0e90:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The earth (world) feels good when the rain shows up.", "output_text": "Ugs'tqamu wela's'g gigpesan nei'a's'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The earth (world) feels good when the rain shows up.", "mic_Latn": "Ugs'tqamu wela's'g gigpesan nei'a's'g." }, "canonical_ref": "entries/g/gigpesan/gigpesan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5c245428a46fa0cee0da", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gigpesan/gigpesan.html", "entry_url": "https://mikmaqonline.org/entries/g/gigpesan/gigpesan.html", "headword": "gigpesan", "example_index": 0, "raw_html_path": "raw/entries/438dda4e2ea3defbb024e58be1895973f574560180aaa3b48bd2b8dbb76b16b1.html", "raw_html_sha256": "6ad5f6fdd0aa7c985ab70f8f70f1f539a84c91e131b8126e2f7f8bc95c158949", "fetched_at": "2026-07-12T02:39:30.618Z", "recordings": [ { "recording_id": "43994b5c454b325a570f5c05c5a5fbe3e333b07ae7876b6d22cce564a6350c5e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cc5/cc5374f44cc7cdc8c9d537d00a3245cb3f3815f33900ab801b006df684509785.mp3", "archive_relative_path": "raw/audio/cc5/cc5374f44cc7cdc8c9d537d00a3245cb3f3815f33900ab801b006df684509785.mp3" } ] } ], "prediction": "Pugwelg'g ta'n tujiw we'gwi'g.", "reference": "Ugs'tqamu wela's'g gigpesan nei'a's'g." }, { "id": "mic-sent-8ad5900f6d5be7f9069f1b62:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It pokes right into the ground.", "output_text": "Lpa ennma's'g maqamigeg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It pokes right into the ground.", "mic_Latn": "Lpa ennma's'g maqamigeg." }, "canonical_ref": "entries/e/ennma's'g/ennma's'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-02832c672254040e226d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/ennma's'g/ennma's'g.html", "entry_url": "https://mikmaqonline.org/entries/e/ennma's'g/ennma's'g.html", "headword": "ennma's'g", "example_index": 0, "raw_html_path": "raw/entries/222aded3f54c6a792b67057076ec0ae78e4c3769658bb728d4c6b4fcd097e9c1.html", "raw_html_sha256": "06a4f9aec4f9151554fbe2f72c521421342bfe82cf6dc97b9ea9c8c8dd4f80a4", "fetched_at": "2026-07-12T02:38:04.297Z", "recordings": [ { "recording_id": "5b797ca6d0ff5a8f1ad47d753608e6ca1a695503a7205b6d0afe105e370112c1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ab5/ab532ca347ab4d97f82bb737fd7c9765afa3f1cc1a59c87b211b10de3cfbcbd3.mp3", "archive_relative_path": "raw/audio/ab5/ab532ca347ab4d97f82bb737fd7c9765afa3f1cc1a59c87b211b10de3cfbcbd3.mp3" } ] } ], "prediction": "Pugwelg'g ta'n tujiw.", "reference": "Lpa ennma's'g maqamigeg." }, { "id": "mic-sent-8b2e6eba7bc2a0331759e964:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Do you know how to use a lacross stick?", "output_text": "Nata'e'wmn wenaqpmaqan?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Do you know how to use a lacross stick?", "mic_Latn": "Nata'e'wmn wenaqpmaqan?" }, "canonical_ref": "entries/w/wenaqpmaqan/wenaqpmaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-731e767193e82f1e98df", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wenaqpmaqan/wenaqpmaqan.html", "entry_url": "https://mikmaqonline.org/entries/w/wenaqpmaqan/wenaqpmaqan.html", "headword": "wenaqpmaqan", "example_index": 0, "raw_html_path": "raw/entries/4bd2b585802da7c7e57601da976c6dac4d6ae6e2f6b82158337ffe6a89a1d432.html", "raw_html_sha256": "87475b7a6700770cbc5afcdf6f5797ef6b6cc5e6c055c49997e1fcd7bf5dd56f", "fetched_at": "2026-07-12T02:47:12.237Z", "recordings": [ { "recording_id": "a55c6e44c375b041d5856cebaf510d119794a89e48c888203b7127503ef1b41b", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/306/3069065b24afd350377e4541338052a2ad0b94367a2c9bcd7d2bc7e8f7308ab1.mp3", "archive_relative_path": "raw/audio/306/3069065b24afd350377e4541338052a2ad0b94367a2c9bcd7d2bc7e8f7308ab1.mp3" } ] } ], "prediction": "Ge' gi'l ta'n tujiw ala'toq?", "reference": "Nata'e'wmn wenaqpmaqan?" }, { "id": "mic-sent-8bd5c1956b5630af5d2a29c7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "We had a good time at Christmas.", "output_text": "Gisoltie'g Nuelewumgeg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "We had a good time at Christmas.", "mic_Latn": "Gisoltie'g Nuelewumgeg." }, "canonical_ref": "entries/g/gise'g/gise'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c29011ca1627e8084639", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gise'g/gise'g.html", "entry_url": "https://mikmaqonline.org/entries/g/gise'g/gise'g.html", "headword": "gise'g", "example_index": 0, "raw_html_path": "raw/entries/087ba7f995048823d13a3bb2cbd7c10075770e985e163610f4781ba5d3448101.html", "raw_html_sha256": "7654d24fc0521c59d593360c1c8fcf3ddf7d9b58f35fb44a011247f6ba78b9f7", "fetched_at": "2026-07-12T02:39:36.653Z", "recordings": [ { "recording_id": "89e250b8578850631629acaf524c46c48bde624b4947dcec240d472bb9c47ca2", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b5b/b5b8dd509526b3f0db95e9aca686ddf44bd3d5f12ad4b764194e7f48996769ab.mp3", "archive_relative_path": "raw/audio/b5b/b5b8dd509526b3f0db95e9aca686ddf44bd3d5f12ad4b764194e7f48996769ab.mp3" } ] } ], "prediction": "We'gwi'g na Nuelewumg.", "reference": "Gisoltie'g Nuelewumgeg." }, { "id": "mic-sent-8c107987255a7a9f9692405b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she uses his/her new car for work", "output_text": "Pilei utepaqan elugwetoq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she uses his/her new car for work", "mic_Latn": "Pilei utepaqan elugwetoq." }, "canonical_ref": "entries/e/elugwetoq/elugwetoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a8f689271b131315e6e5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elugwetoq/elugwetoq.html", "entry_url": "https://mikmaqonline.org/entries/e/elugwetoq/elugwetoq.html", "headword": "elugwetoq", "example_index": 0, "raw_html_path": "raw/entries/eba2c351ae295ccb35978c6cf88ae605bd6bad20fdc7c4209c224055a97acac6.html", "raw_html_sha256": "08b0ffe187306cfd94bcd48dee46b27427ce2226d5606a360faa647ddc3e822a", "fetched_at": "2026-07-12T02:37:56.059Z", "recordings": [ { "recording_id": "08475e67d64b384c1f3f576da6b65cac13d4fcf170db0929e6fa52a64ce13248", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/927/927bd44b1d120ccfd396116cde3fafe833c31783bbe5eee0054bcf3604c9fd13.mp3", "archive_relative_path": "raw/audio/927/927bd44b1d120ccfd396116cde3fafe833c31783bbe5eee0054bcf3604c9fd13.mp3" } ] } ], "prediction": "Newte'g utepaqan ugjit ugtugowaqan.", "reference": "Pilei utepaqan elugwetoq." }, { "id": "mic-sent-8c4ba2817a813073b54f4972:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Frank is going up the mountain with a shoulder pack.", "output_text": "Plasua so'qwiet aq pemn'get.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Frank is going up the mountain with a shoulder pack.", "mic_Latn": "Plasua so'qwiet aq pemn'get." }, "canonical_ref": "entries/p/pemn'get/pemn'get.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-43f5b06360ba838be105", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemn'get/pemn'get.html", "entry_url": "https://mikmaqonline.org/entries/p/pemn'get/pemn'get.html", "headword": "pemn'get", "example_index": 0, "raw_html_path": "raw/entries/e3c243f22926bde5de597068520834bf538750425519cfe75c2b2aef08809ef7.html", "raw_html_sha256": "c56fb3d0e5d85d1cd00526c6a60da5ee3798a4e642d42e905ffb0bba5acd1a43", "fetched_at": "2026-07-12T02:43:35.335Z", "recordings": [ { "recording_id": "3ed983628b510cfda3014849b265ccfbfa8fa556fad98e0611efa990170c878b", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fb1/fb19c6461ab31d714e4b58772d33701e2bb4c4cc10f9027f3808b2bcc2c95cfc.mp3", "archive_relative_path": "raw/audio/fb1/fb19c6461ab31d714e4b58772d33701e2bb4c4cc10f9027f3808b2bcc2c95cfc.mp3" } ] } ], "prediction": "Sa'q na'te'g ugt'pugtug.", "reference": "Plasua so'qwiet aq pemn'get." }, { "id": "mic-sent-8c4cd2e64d333f9fc98d7f24:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That's my dog that you're talking about.", "output_text": "Ni'newei na nmu'j wesgumt.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That's my dog that you're talking about.", "mic_Latn": "Ni'newei na nmu'j wesgumt." }, "canonical_ref": "entries/n/ni'newei/ni'newei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e5e4c61f0d9566f9bec2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ni'newei/ni'newei.html", "entry_url": "https://mikmaqonline.org/entries/n/ni'newei/ni'newei.html", "headword": "ni'newei", "example_index": 0, "raw_html_path": "raw/entries/5e7855fd061af2c580bb54b4cda462a02304e906481570685ad2c65962d388d2.html", "raw_html_sha256": "810ee412626af199bbb68ebf5f9f7cd7ae0761cc8ef23f055e2ca33ebb1d100a", "fetched_at": "2026-07-12T02:42:34.421Z", "recordings": [ { "recording_id": "d891ec3514d3ed2221db6f31a842ff2808cd8df8a36fbf32d82c70f8068eae04", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/28a/28a1db11afe29552b080c4158f33fd689297bad9d2620e16e5933e6d26f51050.mp3", "archive_relative_path": "raw/audio/28a/28a1db11afe29552b080c4158f33fd689297bad9d2620e16e5933e6d26f51050.mp3" } ] } ], "prediction": "Nmu'ji'j na ni'n goqwei.", "reference": "Ni'newei na nmu'j wesgumt." }, { "id": "mic-sent-8c5d80d4f3854bd3ae36d107:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There are not too many natives that you can say they are rich.", "output_text": "Mu' pugwelug nnu ta'n gistluetes milesit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There are not too many natives that you can say they are rich.", "mic_Latn": "Mu' pugwelug nnu ta'n gistluetes milesit." }, "canonical_ref": "entries/m/milesit/milesit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-65dd78a1db310c63bc8d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/milesit/milesit.html", "entry_url": "https://mikmaqonline.org/entries/m/milesit/milesit.html", "headword": "milesit", "example_index": 0, "raw_html_path": "raw/entries/5fd501fb5d4b9581ed4f54b1136362c12c1a4b5417598f3071193ffea3658a32.html", "raw_html_sha256": "c2eed00764ddded28a4b2c17eaa9b3e0474638d1f00d93659e1a91d9dcf0d1a5", "fetched_at": "2026-07-12T02:41:36.053Z", "recordings": [ { "recording_id": "ee747dad826363f14541d4d4ac948348e57a053179ff4a6e86b7ce51c732f7be", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/162/162a7d709c9eee7ed46bab55c4ffad968a5c417929020444c3ca1310d5c6b42b.mp3", "archive_relative_path": "raw/audio/162/162a7d709c9eee7ed46bab55c4ffad968a5c417929020444c3ca1310d5c6b42b.mp3" } ] } ], "prediction": "Mu te's'g ta'n tujiw nugu' gisijig.", "reference": "Mu' pugwelug nnu ta'n gistluetes milesit." }, { "id": "mic-sent-8c8ba7a350a5d1085201154b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He\\she is spreading the paint on the floor smoothly.", "output_text": "Weljaqatl na ula amjaqignn msaqtaqtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He\\she is spreading the paint on the floor smoothly.", "mic_Latn": "Weljaqatl na ula amjaqignn msaqtaqtug." }, "canonical_ref": "entries/w/weljaqatl/weljaqatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d6d048c800d720f9d519", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/weljaqatl/weljaqatl.html", "entry_url": "https://mikmaqonline.org/entries/w/weljaqatl/weljaqatl.html", "headword": "weljaqatl", "example_index": 0, "raw_html_path": "raw/entries/15cf622048b7d3a62acfb73b8cef1ed1c2b9d5ba5e4361a63e986c21677169cc.html", "raw_html_sha256": "3619318130cf5666227de9335b6ab6bb5a787f915dda2241b69dd83e766cba20", "fetched_at": "2026-07-12T02:47:04.182Z", "recordings": [ { "recording_id": "81bac3affbabbfe36d1654d663d1df0477a0c84526171af11931db5ed8029484", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/da9/da99dcbfacfa6e7c01c2b5e86159a226ce87ca6a3c6aedca88535b88387cd53b.mp3", "archive_relative_path": "raw/audio/da9/da99dcbfacfa6e7c01c2b5e86159a226ce87ca6a3c6aedca88535b88387cd53b.mp3" } ] } ], "prediction": "Pugwelga'latl ugtaqanigtug.", "reference": "Weljaqatl na ula amjaqignn msaqtaqtug." }, { "id": "mic-sent-8c95b0353d0724e45d646044:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I think that this canoe is too narrow and shallow..", "output_text": "Telte'tm wesamjijigulqeg ula gwitn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I think that this canoe is too narrow and shallow..", "mic_Latn": "Telte'tm wesamjijigulqeg ula gwitn." }, "canonical_ref": "entries/j/jijigulqeg/jijigulqeg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b831c1fd25bfe81dbd24", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jijigulqeg/jijigulqeg.html", "entry_url": "https://mikmaqonline.org/entries/j/jijigulqeg/jijigulqeg.html", "headword": "jijigulqeg", "example_index": 0, "raw_html_path": "raw/entries/7fc6d2f9f16ef189965b149c85d91716b5da5eda85035c87387c03a044252cc5.html", "raw_html_sha256": "f5fa2142eef9578e8ef5fda15cd5d09d60078e5de76f9ad99e45e158019247ec", "fetched_at": "2026-07-12T02:40:20.009Z", "recordings": [ { "recording_id": "f9ff3bb25dfa333e7921bc5fdbd6ccaccf335c95555e5f73f51d24527c5bc324", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/458/458f7c435f02f0ebcdaa5c0430cedd16504e04ac7ef53aa0e478900e031e760c.mp3", "archive_relative_path": "raw/audio/458/458f7c435f02f0ebcdaa5c0430cedd16504e04ac7ef53aa0e478900e031e760c.mp3" } ] } ], "prediction": "Telte's'g na ula gmu'j gesatg aq mesga'toq.", "reference": "Telte'tm wesamjijigulqeg ula gwitn." }, { "id": "mic-sent-8cb89368aa913e30ceff08ef:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Use this extremely good one.", "output_text": "Ula pajijiglulg e'we'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Use this extremely good one.", "mic_Latn": "Ula pajijiglulg e'we'n." }, "canonical_ref": "entries/p/pajijiglulg/pajijiglulg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ab2f3f03ab960b86697d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pajijiglulg/pajijiglulg.html", "entry_url": "https://mikmaqonline.org/entries/p/pajijiglulg/pajijiglulg.html", "headword": "pajijiglulg", "example_index": 0, "raw_html_path": "raw/entries/58b24f018d12fc4c766816bff2bc6eff13034f9c048e7cd48784c103a2af94a3.html", "raw_html_sha256": "113f10be107e455f307f4b20bb76b1361203fd5821d1e812423b23bfd42289cc", "fetched_at": "2026-07-12T02:43:03.976Z", "recordings": [ { "recording_id": "229c2368dad3f320a309fcc81abda8ad6ce4e3a87fd5aaefb634c516b6843a1f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b28/b283f5ff9d8bd2a0a9daa5f521af23388c99e013f3e450bf6179f9b712228060.mp3", "archive_relative_path": "raw/audio/b28/b283f5ff9d8bd2a0a9daa5f521af23388c99e013f3e450bf6179f9b712228060.mp3" } ] } ], "prediction": "Amujpa na ula gmu'ji'j.", "reference": "Ula pajijiglulg e'we'n." }, { "id": "mic-sent-8ce5e41d858c3e8b1e80584b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I'm scraping off the gum even if it is stuck on really tight.", "output_text": "Mena'qigwalg pgu tlia' segg'naspij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I'm scraping off the gum even if it is stuck on really tight.", "mic_Latn": "Mena'qigwalg pgu tlia' segg'naspij." }, "canonical_ref": "entries/m/mena'qigwalatl/mena'qigwalatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f618616bd87fa43db8e8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mena'qigwalatl/mena'qigwalatl.html", "entry_url": "https://mikmaqonline.org/entries/m/mena'qigwalatl/mena'qigwalatl.html", "headword": "mena'qigwalatl", "example_index": 0, "raw_html_path": "raw/entries/4f74f56ba5b3b8c76f2f8f1321ef933223579cbaa9ebd263dbd835d4010104e8.html", "raw_html_sha256": "adc67220c3fe267b8e065ecb5bf4741808fda2f7c9ca20914a74da417bc374a6", "fetched_at": "2026-07-12T02:41:15.402Z", "recordings": [ { "recording_id": "e0996d9f5e5588f312d781fbc836ce8dec118a6eb82730d49a7df007a9827e79", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a81/a81b0cf55bd6cfc38ad6bc8c81c722e5b0b1ef629ce8d8648fba87d143cc9438.mp3", "archive_relative_path": "raw/audio/a81/a81b0cf55bd6cfc38ad6bc8c81c722e5b0b1ef629ce8d8648fba87d143cc9438.mp3" } ] } ], "prediction": "Pugwelg'p na gmu'j ta'n tujiw gesatg.", "reference": "Mena'qigwalg pgu tlia' segg'naspij." }, { "id": "mic-sent-8d5c9293341f389c74b30c70:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A new house is echoey while its empty.", "output_text": "Pilei wenji'guom paqtaqawa'q ge's sigue'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A new house is echoey while its empty.", "mic_Latn": "Pilei wenji'guom paqtaqawa'q ge's sigue'g." }, "canonical_ref": "entries/p/paqtaqawa'q/paqtaqawa'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-92ed0b1281c9009e2c21", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/paqtaqawa'q/paqtaqawa'q.html", "entry_url": "https://mikmaqonline.org/entries/p/paqtaqawa'q/paqtaqawa'q.html", "headword": "paqtaqawa'q", "example_index": 0, "raw_html_path": "raw/entries/9981340b7c36fd6441fec01247b9c189b04a2c0042a8dc547aa504205bf35f41.html", "raw_html_sha256": "75e87e8ec8b0fb4833ef4181ceb43113e6ffbb31038f2a60bf10b2793e6a7082", "fetched_at": "2026-07-12T02:43:12.213Z", "recordings": [ { "recording_id": "a8f1c5d9075e24cb2da52cc413105861e2af1aa7929b194e699f9fe2aea8401a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9a0/9a06301d9c802f54db01542de3c6a19d19d6159a919f33075cedbcca321f1d85.mp3", "archive_relative_path": "raw/audio/9a0/9a06301d9c802f54db01542de3c6a19d19d6159a919f33075cedbcca321f1d85.mp3" } ] } ], "prediction": "Pilei we'gwi's'g ta'n tujiw e'w'g.", "reference": "Pilei wenji'guom paqtaqawa'q ge's sigue'g." }, { "id": "mic-sent-8dfc1b96a04da85f09ea25d6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You could say the one coming by canoe is having a good time.", "output_text": "Tluenes we'gwigsalsit na wejgwigwitna'q.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You could say the one coming by canoe is having a good time.", "mic_Latn": "Tluenes we'gwigsalsit na wejgwigwitna'q." }, "canonical_ref": "entries/w/wejgwigwitna'q/wejgwigwitna'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bc01bf8cfe56545048bc", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejgwigwitna'q/wejgwigwitna'q.html", "entry_url": "https://mikmaqonline.org/entries/w/wejgwigwitna'q/wejgwigwitna'q.html", "headword": "wejgwigwitna'q", "example_index": 0, "raw_html_path": "raw/entries/cd79a73090b53dd0a3e438451cd2a9837719ad66f493da770aa2949271638211.html", "raw_html_sha256": "5bf31c0dd245a87c0d6a7459cdf4a35e47ebbbd0df1514b6230b231c6f93492c", "fetched_at": "2026-07-12T02:46:51.493Z", "recordings": [ { "recording_id": "7a1e8b2dac42a9765390933c2ddfe9497a6274e0cb8aa55be5b33bade11fd7cb", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/91a/91a9cc55b8fc22e19476aaa0b51e369f74a977fd8f9cd5977d48cef1847397d1.mp3", "archive_relative_path": "raw/audio/91a/91a9cc55b8fc22e19476aaa0b51e369f74a977fd8f9cd5977d48cef1847397d1.mp3" } ] } ], "prediction": "Ge's goqwei ta'n tujiw na'te'g.", "reference": "Tluenes we'gwigsalsit na wejgwigwitna'q." }, { "id": "mic-sent-8e03932303abb2c925b47521:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend here likes to brag and has a somewhat high opinion of himself/herself.", "output_text": "Ula nitap mawinta'ginuet aq gimu'tug megitelsit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend here likes to brag and has a somewhat high opinion of himself/herself.", "mic_Latn": "Ula nitap mawinta'ginuet aq gimu'tug megitelsit." }, "canonical_ref": "entries/m/megitelsit/megitelsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c99c140f53a0611caaa6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/megitelsit/megitelsit.html", "entry_url": "https://mikmaqonline.org/entries/m/megitelsit/megitelsit.html", "headword": "megitelsit", "example_index": 0, "raw_html_path": "raw/entries/73bf609deafa6885ca7743cb9c37e433f0748adb0b8086c676212faa5da4b3e1.html", "raw_html_sha256": "2cf3a726a190bd495150a3a2934a348a2cfb21d5958a5a35bdab9b43abf93b82", "fetched_at": "2026-07-12T02:41:06.843Z", "recordings": [ { "recording_id": "71eb6e988ac5a70ead1b037aaacc6ad6aeffe873eb5544ced645f0fbdbcddb77", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0b6/0b696b48959b0d45e0551179ece6a2e96656373e9d7811c992a5a20e576d9427.mp3", "archive_relative_path": "raw/audio/0b6/0b696b48959b0d45e0551179ece6a2e96656373e9d7811c992a5a20e576d9427.mp3" } ] } ], "prediction": "Ula nitap gesgm'g aq mesgi'gigtug.", "reference": "Ula nitap mawinta'ginuet aq gimu'tug megitelsit." }, { "id": "mic-sent-8e0d296949f69cada5876d0a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My dog is protective of my grandchild.", "output_text": "Nti geleiwatl nuji'jl", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My dog is protective of my grandchild.", "mic_Latn": "Nti geleiwatl nuji'jl" }, "canonical_ref": "entries/g/geleiwatl/geleiwatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-792fdd92bbd875fd4c59", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/geleiwatl/geleiwatl.html", "entry_url": "https://mikmaqonline.org/entries/g/geleiwatl/geleiwatl.html", "headword": "geleiwatl", "example_index": 0, "raw_html_path": "raw/entries/81c10e9f9defc44d297510c9a54c0b31bd32586bfc6ee4b3f66c367f0aa734a1.html", "raw_html_sha256": "3846210ce66ff79e8a74deebbf7bcfeca74beb0f77fcbc5ebc1400dde717f4b1", "fetched_at": "2026-07-12T02:38:55.268Z", "recordings": [ { "recording_id": "b8d3da0a2813cfb3be67d9b053bfffb8efa21b8349df3605fd70e67766b19bd6", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9be/9be3685cd469250e67a1763112db32af735c3205d7225c8c2ea39994058602a7.mp3", "archive_relative_path": "raw/audio/9be/9be3685cd469250e67a1763112db32af735c3205d7225c8c2ea39994058602a7.mp3" } ] } ], "prediction": "Nti gesatg nugu'ji'j.", "reference": "Nti geleiwatl nuji'jl" }, { "id": "mic-sent-8e1eb96a428d37c9d8354004:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where I live the ground is wet.", "output_text": "Saqpejaqamig na ta'n wigi.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where I live the ground is wet.", "mic_Latn": "Saqpejaqamig na ta'n wigi." }, "canonical_ref": "entries/s/saqpejaqamig/saqpejaqamig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0c79675ba6ded0b158fa", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/saqpejaqamig/saqpejaqamig.html", "entry_url": "https://mikmaqonline.org/entries/s/saqpejaqamig/saqpejaqamig.html", "headword": "saqpejaqamig", "example_index": 0, "raw_html_path": "raw/entries/fb918cb2dbfcae4cab4d75251fdf042e7215b6d387eddc0ac75703ac6f140253.html", "raw_html_sha256": "894cfe40105ac3dd3cc8e26d62e05678f72ef25f1fdd26779df3a06cf7760703", "fetched_at": "2026-07-12T02:44:43.044Z", "recordings": [ { "recording_id": "27ee642abb70dd7645256ff22aa2ead5ef8ee336d3062f0384d3d011d6ac66b0", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/efe/efe5411c1f363589181557acf448aa8a64414215a5629af402bf9c416d6253fe.mp3", "archive_relative_path": "raw/audio/efe/efe5411c1f363589181557acf448aa8a64414215a5629af402bf9c416d6253fe.mp3" } ] } ], "prediction": "Ta'n te'sipow ta'n tujiw gisgugwet.", "reference": "Saqpejaqamig na ta'n wigi." }, { "id": "mic-sent-8e4ae9699ebf5f31cfb96e7c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she decorates the little tree for Christmas.", "output_text": "Gegna'latl miti'ji'tl ugjit Nuelewumg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she decorates the little tree for Christmas.", "mic_Latn": "Gegna'latl miti'ji'tl ugjit Nuelewumg." }, "canonical_ref": "entries/g/gegna'latl/gegna'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-086abaf15b38629b84df", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gegna'latl/gegna'latl.html", "entry_url": "https://mikmaqonline.org/entries/g/gegna'latl/gegna'latl.html", "headword": "gegna'latl", "example_index": 0, "raw_html_path": "raw/entries/5516d1e10c238341803f2a892b8bdd3ea596f2397481e7af490969076a89941f.html", "raw_html_sha256": "441a4e6ff33c1e122a49fd61227bcadeb90082a22d669fb8556a1fb280ae2b92", "fetched_at": "2026-07-12T02:38:48.838Z", "recordings": [ { "recording_id": "d736ea34474a970d70e4e5070b5b737e9d8ab853dcdc95910bfc8d2167ebcd8a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b91/b91e7351b36101b139e1badbb3e6adfa12c1b80b110d8b4d5d76435f89515b21.mp3", "archive_relative_path": "raw/audio/b91/b91e7351b36101b139e1badbb3e6adfa12c1b80b110d8b4d5d76435f89515b21.mp3" } ] } ], "prediction": "E'wji'jg na miti'j na Nuelewumg.", "reference": "Gegna'latl miti'ji'tl ugjit Nuelewumg." }, { "id": "mic-sent-8efe5d475a72916cbce12294:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend here takes a long time whenever he/she goes anywhere.", "output_text": "Ula nitap na maw pegittoq ta'n tujiw tami eliej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend here takes a long time whenever he/she goes anywhere.", "mic_Latn": "Ula nitap na maw pegittoq ta'n tujiw tami eliej." }, "canonical_ref": "entries/p/pegittoq/pegittoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c194d7bc833753e8887a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pegittoq/pegittoq.html", "entry_url": "https://mikmaqonline.org/entries/p/pegittoq/pegittoq.html", "headword": "pegittoq", "example_index": 0, "raw_html_path": "raw/entries/28ac983b317a743a6025d0b761bdd95dd9c78d32fb0ab6f7661ba2cf91c261ae.html", "raw_html_sha256": "462d2fb147f41fe292bed76e4011a36037c6efb322e83a35b9d3068cc39ff87f", "fetched_at": "2026-07-12T02:43:22.164Z", "recordings": [ { "recording_id": "501672cb4162e609f728479e649f70cfdd714bfe2962a868c2b89b4dd3c3f2ae", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/08c/08c5610b0faf404c5db85e92e75a55666934c25f8c4f8bbc1d45e2e8c867ff26.mp3", "archive_relative_path": "raw/audio/08c/08c5610b0faf404c5db85e92e75a55666934c25f8c4f8bbc1d45e2e8c867ff26.mp3" } ] } ], "prediction": "Ula nitap na te's'g ta'n tujiw goqwei.", "reference": "Ula nitap na maw pegittoq ta'n tujiw tami eliej." }, { "id": "mic-sent-8f33b15c91637ffd6d96a61b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "\"He/she has been very unfaithful\" is the name of this book.", "output_text": "\"Gis ma'munisespo'teget\" na teluisig na ula wi'gatign.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "\"He/she has been very unfaithful\" is the name of this book.", "mic_Latn": "\"Gis ma'munisespo'teget\" na teluisig na ula wi'gatign." }, "canonical_ref": "entries/s/sespo'teget/sespo'teget.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0565d3648a7cf973dab0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sespo'teget/sespo'teget.html", "entry_url": "https://mikmaqonline.org/entries/s/sespo'teget/sespo'teget.html", "headword": "sespo'teget", "example_index": 1, "raw_html_path": "raw/entries/1d7e01b88287a56bf8f513e556eaaf16c290f78218fa6125689279f20a451d0b.html", "raw_html_sha256": "90da0262fc08e5d80009b5fbe5783ef94fc58c400da7d0bdecda0481836eecb5", "fetched_at": "2026-07-12T02:44:53.830Z", "recordings": [ { "recording_id": "34a87fa76994b2cec5c5bfb3dc596ee58dff14dc9f43ab1ab268f00c77acbfed", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/471/471f2e546513119772bdc9254c7a8cce66b1013d92b79e8b35eae6abb78c3269.mp3", "archive_relative_path": "raw/audio/471/471f2e546513119772bdc9254c7a8cce66b1013d92b79e8b35eae6abb78c3269.mp3" } ] } ], "prediction": "\"Tela'sit\" na ula wi'gwi'g.", "reference": "\"Gis ma'munisespo'teget\" na teluisig na ula wi'gatign." }, { "id": "mic-sent-8f4f29cf474ee14722774a0c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I work here.", "output_text": "Ula tett etlugwei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I work here.", "mic_Latn": "Ula tett etlugwei." }, "canonical_ref": "entries/u/ula_tett/ula_tett.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bf86d2dfc27c70893cf3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ula_tett/ula_tett.html", "entry_url": "https://mikmaqonline.org/entries/u/ula_tett/ula_tett.html", "headword": "ula_tett", "example_index": 0, "raw_html_path": "raw/entries/853bc4dade4f3eda7718307dfd0284f9403c47eb92d0b0b99a422f491b1f234a.html", "raw_html_sha256": "c7b6d6250800aa956c569617088aa98110e1711d920d1a9443698d81f1a558d5", "fetched_at": "2026-07-12T02:46:22.465Z", "recordings": [ { "recording_id": "e6b4614d0011fe68033e0a7c347383524ed6ec78034410538b19a20b41ba3e99", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/207/207cffdb57ea5cbfd6b6f0de0592f8e1bee9a0cb41159f01644da2a394eebe5d.mp3", "archive_relative_path": "raw/audio/207/207cffdb57ea5cbfd6b6f0de0592f8e1bee9a0cb41159f01644da2a394eebe5d.mp3" } ] } ], "prediction": "Gi's na ula tet.", "reference": "Ula tett etlugwei." }, { "id": "mic-sent-8fc3df219fe0e1264f1282b1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Don't choose that one, it is in extrememly bad shape, take the other one.", "output_text": "Mut mgnaw na, pajijiwinjit, ala igtig ugsua'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Don't choose that one, it is in extrememly bad shape, take the other one.", "mic_Latn": "Mut mgnaw na, pajijiwinjit, ala igtig ugsua'l." }, "canonical_ref": "entries/p/pajijiwinjit/pajijiwinjit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f6946e940db4367d5696", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pajijiwinjit/pajijiwinjit.html", "entry_url": "https://mikmaqonline.org/entries/p/pajijiwinjit/pajijiwinjit.html", "headword": "pajijiwinjit", "example_index": 0, "raw_html_path": "raw/entries/2e3cc2d937550a87b4b4988adbe5981f9b39ffd11ab35dfd830c18e8a8fb2269.html", "raw_html_sha256": "1afa27c3001871f44577728dac0fd37e94fc933fdb7fa2b869e786a0b404b86e", "fetched_at": "2026-07-12T02:43:04.576Z", "recordings": [ { "recording_id": "1d45fd4820c56b3bd04229f20b82ffd8557637792196f628494651982115b778", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/06a/06a6e513f0a155c14cf7e589c79bcaa32db6697da84887d9fd0e0da98783ff24.mp3", "archive_relative_path": "raw/audio/06a/06a6e513f0a155c14cf7e589c79bcaa32db6697da84887d9fd0e0da98783ff24.mp3" } ] } ], "prediction": "Mut nuta'toq na, na mawji'jig, gisi'l na'te'l.", "reference": "Mut mgnaw na, pajijiwinjit, ala igtig ugsua'l." }, { "id": "mic-sent-90053fadd027e3597d605cbd:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The photograph is so old it's fading away.", "output_text": "Napui'gign telsa'qawei lpa gesgamugwiet nugu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The photograph is so old it's fading away.", "mic_Latn": "Napui'gign telsa'qawei lpa gesgamugwiet nugu." }, "canonical_ref": "entries/g/gesgamugwiet/gesgamugwiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bcfd71377d777a61cff8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesgamugwiet/gesgamugwiet.html", "entry_url": "https://mikmaqonline.org/entries/g/gesgamugwiet/gesgamugwiet.html", "headword": "gesgamugwiet", "example_index": 0, "raw_html_path": "raw/entries/77b04b440b0e16475109ec4b6734c5200b35baad16b979aa884e5f7d1c4c2036.html", "raw_html_sha256": "8d7f82614c8b732719d18ca4605f4199c8a814835591ebfe993a2a1340a72229", "fetched_at": "2026-07-12T02:39:04.608Z", "recordings": [ { "recording_id": "afa5ba02ef05af23786e834d14dd34a1eafe6fe4d7a63231c662bbeffaf6d99c", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/435/435e806621be052407e5b639c2e1dd1a3d6a00fb96045e9703869699b2f2cd5b.mp3", "archive_relative_path": "raw/audio/435/435e806621be052407e5b639c2e1dd1a3d6a00fb96045e9703869699b2f2cd5b.mp3" } ] } ], "prediction": "Tetuji'jg na ula foto'gwe'g ta'n tujiw gesatg.", "reference": "Napui'gign telsa'qawei lpa gesgamugwiet nugu." }, { "id": "mic-sent-9019bc015fa073281355b9c5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where's the bait?", "output_text": "Waqatign tami eteg?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where's the bait?", "mic_Latn": "Waqatign tami eteg?" }, "canonical_ref": "entries/w/waqatign/waqatign.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f54dcf4f5c4392035675", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waqatign/waqatign.html", "entry_url": "https://mikmaqonline.org/entries/w/waqatign/waqatign.html", "headword": "waqatign", "example_index": 0, "raw_html_path": "raw/entries/1933de5a1160750f8982bb7ebde49d3fac6a79a396439d0b87a2e586b7cfd08b.html", "raw_html_sha256": "2cfb34c46f27e6ab798fe0cafe1b426b1cb227008792aac5ff1baa1981f912e9", "fetched_at": "2026-07-12T02:46:40.044Z", "recordings": [ { "recording_id": "ae9e6a0932b50299fcf2eea5f55bee40c4add6956dba0d12fc72062774ff8c99", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/103/10392626f713d4384d3499962b0b2588ae38123cb3c58bf585facf7bf525f7f3.mp3", "archive_relative_path": "raw/audio/103/10392626f713d4384d3499962b0b2588ae38123cb3c58bf585facf7bf525f7f3.mp3" } ] } ], "prediction": "Tami eteg?", "reference": "Waqatign tami eteg?" }, { "id": "mic-sent-90ade2cd2fa18db777a31bbb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Joseph keeps a light on his net while he's fishing.", "output_text": "Sosep wasoqonatl ugta'piml ge's etla'pigej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Joseph keeps a light on his net while he's fishing.", "mic_Latn": "Sosep wasoqonatl ugta'piml ge's etla'pigej." }, "canonical_ref": "entries/w/wasoqonatl/wasoqonatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-66793b9579b9a8b24e27", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wasoqonatl/wasoqonatl.html", "entry_url": "https://mikmaqonline.org/entries/w/wasoqonatl/wasoqonatl.html", "headword": "wasoqonatl", "example_index": 0, "raw_html_path": "raw/entries/93a5bcd816d3abda2793dfbb6ba5914cfca23fbb0f851c0e1eb5b277d4b51794.html", "raw_html_sha256": "d0729149ac3c7b6f7f75ce762e26403f153aba7c0f18f8ce77ca443a65d7df23", "fetched_at": "2026-07-12T02:46:42.070Z", "recordings": [ { "recording_id": "8a5e262dcbcd74757059e25c818ef24d909dc38730fcd1b75f96d0feca66823f", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8e3/8e3571c7f4dc9b8ecadc25cc236732af8a09da32a4e76eb6819955cc38f36a81.mp3", "archive_relative_path": "raw/audio/8e3/8e3571c7f4dc9b8ecadc25cc236732af8a09da32a4e76eb6819955cc38f36a81.mp3" } ] } ], "prediction": "So'sep gesatg ugta'latl ugjitl ta'n tujiw pugsugwet.", "reference": "Sosep wasoqonatl ugta'piml ge's etla'pigej." }, { "id": "mic-sent-90ca9b871ad661713dfa986e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's good to fight for what you believe in.", "output_text": "Gelu'lg wen igatg ta'n teligtlams'tasij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's good to fight for what you believe in.", "mic_Latn": "Gelu'lg wen igatg ta'n teligtlams'tasij." }, "canonical_ref": "entries/i/igatg/igatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0d9a6d2c5c94e1112d01", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/igatg/igatg.html", "entry_url": "https://mikmaqonline.org/entries/i/igatg/igatg.html", "headword": "igatg", "example_index": 0, "raw_html_path": "raw/entries/aae20d6492eb687c44e78a79b6a9fe28cee3ef34e1046cdc31a513c073ff6b6d.html", "raw_html_sha256": "1f7600bb39105b5c4ed99efb68ebf89f2ad2dc7e2f0f65d1aca55c160409732b", "fetched_at": "2026-07-12T02:40:04.815Z", "recordings": [ { "recording_id": "239b1b96823a2fdbc5d239beccdba6bffba4232032c882c25e433a3f5fac865d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/178/1789c1c60c067e746203584ba1a8f2d0c0c01866b2b8e22387c18aec8049fbf4.mp3", "archive_relative_path": "raw/audio/178/1789c1c60c067e746203584ba1a8f2d0c0c01866b2b8e22387c18aec8049fbf4.mp3" } ] } ], "prediction": "Me' we'gwi'g ta'n tujiw gisijig.", "reference": "Gelu'lg wen igatg ta'n teligtlams'tasij." }, { "id": "mic-sent-91294e09aa735217d990f316:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Let's go upstairs, it's still a little warm.", "output_text": "Ge'gwe'g lta'nej, me' ijga epoqeg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Let's go upstairs, it's still a little warm.", "mic_Latn": "Ge'gwe'g lta'nej, me' ijga epoqeg." }, "canonical_ref": "entries/e/epoqeg/epoqeg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c9b396e1d608ced4a0cb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/epoqeg/epoqeg.html", "entry_url": "https://mikmaqonline.org/entries/e/epoqeg/epoqeg.html", "headword": "epoqeg", "example_index": 0, "raw_html_path": "raw/entries/1d5a7b2552261254035be741550a251d599933c12fa6854eb1471ffe3847be37.html", "raw_html_sha256": "e475cf8d1b548f49a74e8701c60fb3bf3d15098e11029ee95939616f71b98b7e", "fetched_at": "2026-07-12T02:38:09.629Z", "recordings": [ { "recording_id": "6490b90804a0a3ca63a51c182ba1e06988d12518bd524ccbf69faf75903ce081", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0e8/0e88c8fd656c31e6841d38b463b6f64540d130396cbfe814594a4d7cc441ad02.mp3", "archive_relative_path": "raw/audio/0e8/0e88c8fd656c31e6841d38b463b6f64540d130396cbfe814594a4d7cc441ad02.mp3" } ] } ], "prediction": "Ge' gisgug, gi's me' we'gwi'g.", "reference": "Ge'gwe'g lta'nej, me' ijga epoqeg." }, { "id": "mic-sent-91298fde81da3f9ccae641af:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she opens a jam bottle and immediaely starts to spread it on (for himself/herself).", "output_text": "Pasgoqsigne'l pu'tail pana'latl aq smtug amjaqamat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she opens a jam bottle and immediaely starts to spread it on (for himself/herself).", "mic_Latn": "Pasgoqsigne'l pu'tail pana'latl aq smtug amjaqamat." }, "canonical_ref": "entries/p/pana'latl/pana'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-08e46bb5ac3635012dfa", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pana'latl/pana'latl.html", "entry_url": "https://mikmaqonline.org/entries/p/pana'latl/pana'latl.html", "headword": "pana'latl", "example_index": 0, "raw_html_path": "raw/entries/37e668b226df912bfcf1a89df5a01451dbca9d620876fdb3bab062706c7f31e6.html", "raw_html_sha256": "bd065ac0862e5e5c958f8597360168e8d1bfc63f39804f213a60b59253bc9f0f", "fetched_at": "2026-07-12T02:43:05.179Z", "recordings": [ { "recording_id": "de6a6a7980772744c4a3872183df4a8520d1f4e69f94986d7df6fc0d17decbd7", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/527/5277e8724ab22f47f224b314a09b91b38f62e2ce74bc3c034e4367b648db15d1.mp3", "archive_relative_path": "raw/audio/527/5277e8724ab22f47f224b314a09b91b38f62e2ce74bc3c034e4367b648db15d1.mp3" } ] } ], "prediction": "Pugwelga'latl ugjit aq pas'g etlmisga'toq.", "reference": "Pasgoqsigne'l pu'tail pana'latl aq smtug amjaqamat." }, { "id": "mic-sent-918011638658d32310e87306:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is really pleased to see his/her home, he/she has been gone so long.", "output_text": "Lpa pe'gwapt'g wi'g, tewgisa'q maja'sit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is really pleased to see his/her home, he/she has been gone so long.", "mic_Latn": "Lpa pe'gwapt'g wi'g, tewgisa'q maja'sit." }, "canonical_ref": "entries/p/pe'gwapt'g/pe'gwapt'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5630b3cd0d6f7ac81b90", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pe'gwapt'g/pe'gwapt'g.html", "entry_url": "https://mikmaqonline.org/entries/p/pe'gwapt'g/pe'gwapt'g.html", "headword": "pe'gwapt'g", "example_index": 0, "raw_html_path": "raw/entries/b1e862c65cf0a8fe9b619885523288c73f37cdc31ac83a117b25ce067312336b.html", "raw_html_sha256": "5e99a3f60134134a3b6635bf10e6432704c84dd2f6d5e1ad918e8d1db29b1819", "fetched_at": "2026-07-12T02:43:23.156Z", "recordings": [ { "recording_id": "916b45c961e6bd78485463e41535b9d002c0163d2b3270ac36dc4b8a5c970ec0", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/be0/be01e6dabbd84c93e482d8f51c385c7b50879928afd8670cae2acb87ce9f730a.mp3", "archive_relative_path": "raw/audio/be0/be01e6dabbd84c93e482d8f51c385c7b50879928afd8670cae2acb87ce9f730a.mp3" } ] } ], "prediction": "We'gwi'g ta'n newte'l ugjit, te's te'sijig.", "reference": "Lpa pe'gwapt'g wi'g, tewgisa'q maja'sit." }, { "id": "mic-sent-9216b183001d7a6932ea4563:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Every fall, Peter hunts bear.", "output_text": "Te's toqwa'g Pie'l gesgusgwet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Every fall, Peter hunts bear.", "mic_Latn": "Te's toqwa'g Pie'l gesgusgwet." }, "canonical_ref": "entries/g/gesgusgwet/gesgusgwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6e988c648547052b332b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesgusgwet/gesgusgwet.html", "entry_url": "https://mikmaqonline.org/entries/g/gesgusgwet/gesgusgwet.html", "headword": "gesgusgwet", "example_index": 0, "raw_html_path": "raw/entries/fab5c3f2c7a93e91a95c0c6ac826dd7b68f684162b527d86513f3909fd1be472.html", "raw_html_sha256": "0ad1aad9e7e45a4823f06097b0d4ccb3980dd2e2a7e590daf495f16546dca88b", "fetched_at": "2026-07-12T02:36:24.036Z", "recordings": [ { "recording_id": "4abaaad9b6109a343a3213286c18b651d2d829950ffbd0e0421ccbb0fd2452be", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6cf/6cf319e8a62d498c2b3cf0ff4125ef6aac9a639a3c5bcdca0b597ec9fd601965.mp3", "archive_relative_path": "raw/audio/6cf/6cf319e8a62d498c2b3cf0ff4125ef6aac9a639a3c5bcdca0b597ec9fd601965.mp3" } ] } ], "prediction": "Te's te's'g, Pie'l na'te'l ugjit.", "reference": "Te's toqwa'g Pie'l gesgusgwet." }, { "id": "mic-sent-9218609f1b47fbc720731cd6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Could you move over a little bit, your standing on my foot.", "output_text": "Ge'ijga'jijg atpugua'si, pasgmuin ngat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Could you move over a little bit, your standing on my foot.", "mic_Latn": "Ge'ijga'jijg atpugua'si, pasgmuin ngat." }, "canonical_ref": "entries/g/gijga'jijg/gijga'jijg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-179cbe021fad914f4824", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gijga'jijg/gijga'jijg.html", "entry_url": "https://mikmaqonline.org/entries/g/gijga'jijg/gijga'jijg.html", "headword": "gijga'jijg", "example_index": 0, "raw_html_path": "raw/entries/cd651966012a1b5e430c11d22e907828f77b1deb6dc99fbe8717b8965655cff8.html", "raw_html_sha256": "59ad0583c698d116fc5e260576787fa397235edc455805319e4e4194014d3a82", "fetched_at": "2026-07-12T02:39:31.430Z", "recordings": [ { "recording_id": "c01942a16da556306e2b1060b8176cac7aa02d0c9c0b1d3d6ef8f3c6fcba4daf", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/564/5644ea488075330808d975d113a6fdcd71063b965bbf73b72cb61481fd7e00a7.mp3", "archive_relative_path": "raw/audio/564/5644ea488075330808d975d113a6fdcd71063b965bbf73b72cb61481fd7e00a7.mp3" } ] } ], "prediction": "Ge' jugwa'tu'n tujiw, nugu' pilei.", "reference": "Ge'ijga'jijg atpugua'si, pasgmuin ngat." }, { "id": "mic-sent-924d81f4ea7591fef215c02d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My dog likes to chase everything.", "output_text": "Nti gesatg poqt'tesg'g ms't goqwei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My dog likes to chase everything.", "mic_Latn": "Nti gesatg poqt'tesg'g ms't goqwei." }, "canonical_ref": "entries/p/poqt'tesg'g/poqt'tesg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1ae7bc8c8104100e2567", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/poqt'tesg'g/poqt'tesg'g.html", "entry_url": "https://mikmaqonline.org/entries/p/poqt'tesg'g/poqt'tesg'g.html", "headword": "poqt'tesg'g", "example_index": 0, "raw_html_path": "raw/entries/c26b62eacb6fcaf2e59e715b49af2b42641d1f204c945209acf5edcca7599103.html", "raw_html_sha256": "1e7fdfbaa6029975259a1909a62a501fbbe50c63f9630d6f5b68d62eaefbdfdc", "fetched_at": "2026-07-12T02:44:17.048Z", "recordings": [ { "recording_id": "205619e3056293ca8d73c974cdcec103b767c77fa73e2b2976c2b4be36f12e3a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fd3/fd32a7039a3d24ad60d897523f55c9d2af4278fa355ff4a5ff52315b666c62a9.mp3", "archive_relative_path": "raw/audio/fd3/fd32a7039a3d24ad60d897523f55c9d2af4278fa355ff4a5ff52315b666c62a9.mp3" } ] } ], "prediction": "Nti gesatg ta'n te's'g goqwei.", "reference": "Nti gesatg poqt'tesg'g ms't goqwei." }, { "id": "mic-sent-926085839061d41c0b34736e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she must be angry with me, as soon as I got near he/she quickly moved away.", "output_text": "Amuj wegaiugtuit, telgigja'sianeg lpa smtug ejiglateja'sit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she must be angry with me, as soon as I got near he/she quickly moved away.", "mic_Latn": "Amuj wegaiugtuit, telgigja'sianeg lpa smtug ejiglateja'sit." }, "canonical_ref": "entries/e/ejiglateja'sit/ejiglateja'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-669235c406eee439ad7a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/ejiglateja'sit/ejiglateja'sit.html", "entry_url": "https://mikmaqonline.org/entries/e/ejiglateja'sit/ejiglateja'sit.html", "headword": "ejiglateja'sit", "example_index": 0, "raw_html_path": "raw/entries/3f20c796c405198ef773274439fb06f343ac74cfc4c6841aee86cbc646976d93.html", "raw_html_sha256": "6f2808c3333b62bec6602631fa8b9756db5326dc997145bb249bf784cf0df124", "fetched_at": "2026-07-12T02:37:34.221Z", "recordings": [ { "recording_id": "ab8997d62f4973fd23207c79fa52f97e0a193ba5c5abdb0de6ade17c9176ae7e", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5e7/5e7b53e22c2fa0bbbb3fd12ceb81537dd3fdfab6f85d6910b93f564dfb29c7f4.mp3", "archive_relative_path": "raw/audio/5e7/5e7b53e22c2fa0bbbb3fd12ceb81537dd3fdfab6f85d6910b93f564dfb29c7f4.mp3" } ] } ], "prediction": "Amujpa ni'n gisgug, pas'g we'gwi'g ta'n tujiw mesga'sit.", "reference": "Amuj wegaiugtuit, telgigja'sianeg lpa smtug ejiglateja'sit." }, { "id": "mic-sent-93357f693dfaf3f27f942875:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "These boys really resemble one another.", "output_text": "Ula lpatujg we'gwielatijig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "These boys really resemble one another.", "mic_Latn": "Ula lpatujg we'gwielatijig." }, "canonical_ref": "entries/e/elatijig/elatijig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-cdcba571880540cf034d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elatijig/elatijig.html", "entry_url": "https://mikmaqonline.org/entries/e/elatijig/elatijig.html", "headword": "elatijig", "example_index": 0, "raw_html_path": "raw/entries/10b94b3fa89b1f36dbe7dcccfc85a94a473bbb418aefa028cd0b829578dec22e.html", "raw_html_sha256": "57edd72dfafbfdbe03527acad538cec85fcf45f01bff557e17a50b649e727500", "fetched_at": "2026-07-12T02:37:40.855Z", "recordings": [ { "recording_id": "0903253f8cc9f944bbe95b6323d54b3c515efe5d51915a5fd76d5d64187c3c1e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f1a/f1a04b16b4c7147115174675a5c56e705008c0c3a4785f97932642c1fe3c40db.mp3", "archive_relative_path": "raw/audio/f1a/f1a04b16b4c7147115174675a5c56e705008c0c3a4785f97932642c1fe3c40db.mp3" } ] } ], "prediction": "Ula lpa'tuji'jig we'gwi'g.", "reference": "Ula lpatujg we'gwielatijig." }, { "id": "mic-sent-9360e796b5e8d9ad40badafa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she stayed so long I thought he/she was moving in.", "output_text": "Telipgitqatg telta'siap pisgwiwsit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she stayed so long I thought he/she was moving in.", "mic_Latn": "Telipgitqatg telta'siap pisgwiwsit." }, "canonical_ref": "entries/t/telipgitqatg/telipgitqatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a683d078469db8520ee9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/telipgitqatg/telipgitqatg.html", "entry_url": "https://mikmaqonline.org/entries/t/telipgitqatg/telipgitqatg.html", "headword": "telipgitqatg", "example_index": 0, "raw_html_path": "raw/entries/67df4605efff53d1e0efb3e994a4c25be8956a08366f81e83a2f158e9b4441b5.html", "raw_html_sha256": "0444513028cb04c8172731702977830ca8c01297b98e585c5190634f63f61051", "fetched_at": "2026-07-12T02:45:32.105Z", "recordings": [ { "recording_id": "0c89245464cac178f0fd18510d8d041201ed9c8b414590aeb24b335d598af805", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bca/bca74c09a620bf71e4e07aeed9ede81525d7d9f2a1851043ee8902cce783cf75.mp3", "archive_relative_path": "raw/audio/bca/bca74c09a620bf71e4e07aeed9ede81525d7d9f2a1851043ee8902cce783cf75.mp3" } ] } ], "prediction": "Te's te'sijig telta'sit telte's'g.", "reference": "Telipgitqatg telta'siap pisgwiwsit." }, { "id": "mic-sent-936f0f9f832250bc42a8682b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Your dog bit me this morning.", "output_text": "Ugtue'm gisipqa'lit sepei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Your dog bit me this morning.", "mic_Latn": "Ugtue'm gisipqa'lit sepei." }, "canonical_ref": "entries/p/paqa'latl/paqa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9c80fe261b8a61d1b6e2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/paqa'latl/paqa'latl.html", "entry_url": "https://mikmaqonline.org/entries/p/paqa'latl/paqa'latl.html", "headword": "paqa'latl", "example_index": 0, "raw_html_path": "raw/entries/3e2bf66cc5dbbf31a7a9198a05b3c3fe225bdfa85df2403fe51f4e81efcc79ea.html", "raw_html_sha256": "9d5d3563ec31b23208c16679dc8c0ec69a0f91b66b2f7459cc7cac3cd769d749", "fetched_at": "2026-07-12T02:43:09.803Z", "recordings": [ { "recording_id": "0b44d6759adcf947e226b27c7d7468a76d11cdbaa0e47839f1dffac2372d26a1", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bab/bab4675c7d2f33aad60581f6def0fcb64c14e5fd81bac80b417a15cc65ee58e8.mp3", "archive_relative_path": "raw/audio/bab/bab4675c7d2f33aad60581f6def0fcb64c14e5fd81bac80b417a15cc65ee58e8.mp3" } ] } ], "prediction": "Nmu'ji'j etlmisga'latl ula egsitpu'g.", "reference": "Ugtue'm gisipqa'lit sepei." }, { "id": "mic-sent-937c76a35013c05594c070af:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Canoe ribs are a lot of work to get ready.", "output_text": "Gwitne'l pigaqann mesgi'g lugowaqan gisgaja'tm.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Canoe ribs are a lot of work to get ready.", "mic_Latn": "Gwitne'l pigaqann mesgi'g lugowaqan gisgaja'tm." }, "canonical_ref": "entries/p/pigaqan/pigaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0981c9ef1678e66085e3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pigaqan/pigaqan.html", "entry_url": "https://mikmaqonline.org/entries/p/pigaqan/pigaqan.html", "headword": "pigaqan", "example_index": 0, "raw_html_path": "raw/entries/04a182f221e79de40021247c3773522243b6e5cef513de0f4901d1c1586680c7.html", "raw_html_sha256": "381c397a29d9a6fbbe5159a3cbb22d039fae6f0ed1c5677357028d0ca0a8e6e1", "fetched_at": "2026-07-12T02:36:15.984Z", "recordings": [ { "recording_id": "b475784ab529db5a8acdaccc257381c09e8e8d7243acf12a2481f308b47d3c90", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4a6/4a60a18030bcafdd0d0f656cd3bef139e939bc482ffd91bbcc248b80eeb0736a.mp3", "archive_relative_path": "raw/audio/4a6/4a60a18030bcafdd0d0f656cd3bef139e939bc482ffd91bbcc248b80eeb0736a.mp3" } ] } ], "prediction": "Pugwelgig na mawgwi'g ta'n tujiw ugjit.", "reference": "Gwitne'l pigaqann mesgi'g lugowaqan gisgaja'tm." }, { "id": "mic-sent-93be3846c72a6080bba6a5bd:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I think I will to town tomorrow.", "output_text": "Ni'n telte'tm qame'g lia's sapo'nug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I think I will to town tomorrow.", "mic_Latn": "Ni'n telte'tm qame'g lia's sapo'nug." }, "canonical_ref": "entries/t/telte'tg/telte'tg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-faacb37feefdc7fa31ba", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/telte'tg/telte'tg.html", "entry_url": "https://mikmaqonline.org/entries/t/telte'tg/telte'tg.html", "headword": "telte'tg", "example_index": 0, "raw_html_path": "raw/entries/48fb2c514287bad2df83df7ee994855aede960751ad80bb4db8c2d682e2489eb.html", "raw_html_sha256": "d771474da5507240a438a6d8fab9a9c79521aa9f9af8e33ce494e3a612ac3a29", "fetched_at": "2026-07-12T02:45:34.893Z", "recordings": [ { "recording_id": "66436b6e2951631ae952cd268189b79abc5ee4888e2061e8eae7cef55ea7e949", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dee/deea8d1ebde9249abb04f06754cecba14293c7b4c101b75ae94fb9455c9bb067.mp3", "archive_relative_path": "raw/audio/dee/deea8d1ebde9249abb04f06754cecba14293c7b4c101b75ae94fb9455c9bb067.mp3" } ] } ], "prediction": "Telte'l nipugwe'g gisgug.", "reference": "Ni'n telte'tm qame'g lia's sapo'nug." }, { "id": "mic-sent-93cc35099e9cceab2d924bf0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I don't know if my dog has fleas.", "output_text": "Mu gejiaq nti piggwin.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I don't know if my dog has fleas.", "mic_Latn": "Mu gejiaq nti piggwin." }, "canonical_ref": "entries/p/piggwit/piggwit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a1bb76ed968836cc6f7f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/piggwit/piggwit.html", "entry_url": "https://mikmaqonline.org/entries/p/piggwit/piggwit.html", "headword": "piggwit", "example_index": 0, "raw_html_path": "raw/entries/19161d25beb475df5f4f87a4cca4e9cea57a84873fead5b1d30c9cc49864a951.html", "raw_html_sha256": "0c86240cee5f0ef3a95a698f8ea2d9360405c32b59934561f5106d9a4fe54f2d", "fetched_at": "2026-07-12T02:43:53.614Z", "recordings": [ { "recording_id": "6116e449aea47a1ab6578fe77e9bf7ddeeccc742a5a93d6e409c3a88af412234", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9ba/9ba3e0dc7b79a79dddc5c7a9073e55df52ee7dfd3ca8b27fe8c3f2b41a957674.mp3", "archive_relative_path": "raw/audio/9ba/9ba3e0dc7b79a79dddc5c7a9073e55df52ee7dfd3ca8b27fe8c3f2b41a957674.mp3" } ] } ], "prediction": "Mu gejiaq ge's nmu'ji'j gmu'j.", "reference": "Mu gejiaq nti piggwin." }, { "id": "mic-sent-93fc8efc029cb5476891085c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When he/she tripped, he/she almost shot his/her buddy.", "output_text": "Ta'n tujiw pesoqtesgmateg, suel pe'sguatl witapal.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When he/she tripped, he/she almost shot his/her buddy.", "mic_Latn": "Ta'n tujiw pesoqtesgmateg, suel pe'sguatl witapal." }, "canonical_ref": "entries/p/pe'sguatl/pe'sguatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c3246c8cb8339fa1147c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pe'sguatl/pe'sguatl.html", "entry_url": "https://mikmaqonline.org/entries/p/pe'sguatl/pe'sguatl.html", "headword": "pe'sguatl", "example_index": 0, "raw_html_path": "raw/entries/46ceff974ccea790765bb64d3838d80ad6cca8113222a5667e003612841d4df3.html", "raw_html_sha256": "02f2daffd16c47ef3dec64e9a2d6b57215d263026e586a5b0ce260491ac8eda0", "fetched_at": "2026-07-12T02:43:42.156Z", "recordings": [ { "recording_id": "7ef8752f65767edc7260a72cb341050bc1035f86c6b15504e31383af86dc1d0b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/096/0962a7ac799a1286e7f39fcda19bb39430be6782b8ad9d017d9a8f4b1f2a8a66.mp3", "archive_relative_path": "raw/audio/096/0962a7ac799a1286e7f39fcda19bb39430be6782b8ad9d017d9a8f4b1f2a8a66.mp3" } ] } ], "prediction": "Ta'n tujiw gesatg, pas'g gesatgwa'latl witapal.", "reference": "Ta'n tujiw pesoqtesgmateg, suel pe'sguatl witapal." }, { "id": "mic-sent-94083d317263dee152effafa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "All our water has become lukewarm.", "output_text": "Gaqgisu'pegiaqasneg gsamqwanminu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "All our water has become lukewarm.", "mic_Latn": "Gaqgisu'pegiaqasneg gsamqwanminu." }, "canonical_ref": "entries/g/gisupa'q/gisupa'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0cdd37067c7d00547463", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gisupa'q/gisupa'q.html", "entry_url": "https://mikmaqonline.org/entries/g/gisupa'q/gisupa'q.html", "headword": "gisupa'q", "example_index": 0, "raw_html_path": "raw/entries/8727556815b31b4d0f57312902922fd1b9f83817770a0481f59be82abb9d3106.html", "raw_html_sha256": "c72c5b675afa8620849705f87fb6deced3f7e7aefe1f7a40b991446497ce600c", "fetched_at": "2026-07-12T02:39:43.695Z", "recordings": [ { "recording_id": "92605a5347a46491b9b24fbf7f74f74df182dc19058e7729fca10dd498513dd7", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/660/6600dcbc8124a176d1b3bb9aa938a8d26d6733d7c4eb653b853aacc8b60cc502.mp3", "archive_relative_path": "raw/audio/660/6600dcbc8124a176d1b3bb9aa938a8d26d6733d7c4eb653b853aacc8b60cc502.mp3" } ] } ], "prediction": "Pugwelg'g na we'gwi'g ta'n tujiw.", "reference": "Gaqgisu'pegiaqasneg gsamqwanminu." }, { "id": "mic-sent-944609909a3a871087ce36e9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Look at that, he/she only put two peas there for me.", "output_text": "Ge'l angapte'n, pas'g tapuapsgegl alawe'l iga'tuitl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Look at that, he/she only put two peas there for me.", "mic_Latn": "Ge'l angapte'n, pas'g tapuapsgegl alawe'l iga'tuitl." }, "canonical_ref": "entries/t/tapuapsgegl/tapuapsgegl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-cc23f91c81d92f80c7b9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tapuapsgegl/tapuapsgegl.html", "entry_url": "https://mikmaqonline.org/entries/t/tapuapsgegl/tapuapsgegl.html", "headword": "tapuapsgegl", "example_index": 0, "raw_html_path": "raw/entries/8b4099aa0d178082fb7aa9733c904fd688e9a4b5abd027051e26155d0607b3a3.html", "raw_html_sha256": "2183012f7b5892c22e90952ecb6055ef29ef481cefc008683dd5c212c1a67c22", "fetched_at": "2026-07-12T02:45:22.039Z", "recordings": [ { "recording_id": "cc4680d2ae2caf326d7164f4e8f569cf085386c848f2a81514dff428b296bafc", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/007/00743576397590d6bc06b05c7c2afccfe128d9c278d3c457f65b25f8b75fde88.mp3", "archive_relative_path": "raw/audio/007/00743576397590d6bc06b05c7c2afccfe128d9c278d3c457f65b25f8b75fde88.mp3" } ] } ], "prediction": "Ge' gisga'toq na, pas'g gesatgwa'latl nipugji'j.", "reference": "Ge'l angapte'n, pas'g tapuapsgegl alawe'l iga'tuitl." }, { "id": "mic-sent-9480a82e6d9bf2da085178d9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she always buys him/herself proper food.", "output_text": "Apjiw gegnu'telg wilu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she always buys him/herself proper food.", "mic_Latn": "Apjiw gegnu'telg wilu." }, "canonical_ref": "entries/g/gegnu'telg/gegnu'telg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a7c37dbc78ec3cffe5c3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gegnu'telg/gegnu'telg.html", "entry_url": "https://mikmaqonline.org/entries/g/gegnu'telg/gegnu'telg.html", "headword": "gegnu'telg", "example_index": 0, "raw_html_path": "raw/entries/631d462501bc49985e025cb3ece8d7b4dbad54b8b4043b8a75d0920b5348975f.html", "raw_html_sha256": "ad1aaa44a96d09480232b5a2f2ab97598559cb939f0837083fb7d2530ee8ac24", "fetched_at": "2026-07-12T02:38:50.539Z", "recordings": [ { "recording_id": "db58d0b74d9a15ac3f48d2b6c6443b69e87de5af6540b6c7ec28e8f803604d1c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fa0/fa00c949848d24512c5cb6d424b282929ad2bf3fe8567a342f46ba98cd601d96.mp3", "archive_relative_path": "raw/audio/fa0/fa00c949848d24512c5cb6d424b282929ad2bf3fe8567a342f46ba98cd601d96.mp3" } ] } ], "prediction": "Te's te'sipow ta'n te's'g.", "reference": "Apjiw gegnu'telg wilu." }, { "id": "mic-sent-94ebee244ea5de0f61a284d1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I heard the noises he/she made chopping all night.", "output_text": "Imtewnipete'get, nutaq newtitpa'q.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I heard the noises he/she made chopping all night.", "mic_Latn": "Imtewnipete'get, nutaq newtitpa'q." }, "canonical_ref": "entries/n/nipete'get/nipete'get.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b1d13c5c8eac56aedcff", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nipete'get/nipete'get.html", "entry_url": "https://mikmaqonline.org/entries/n/nipete'get/nipete'get.html", "headword": "nipete'get", "example_index": 0, "raw_html_path": "raw/entries/f5997ad10441d04685cd0b45579f4a025e24778fab9ab3278d7886c9dfdee9ab.html", "raw_html_sha256": "77984b1ff11af154c05c700ea7a713100941255f94ebd15c8136542bb99b50e2", "fetched_at": "2026-07-12T02:36:23.528Z", "recordings": [ { "recording_id": "aa275f3835b51007de3a544fcdc64d1161139754b4e6f8a47cdcf34260208eaf", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d75/d75d03a7cec7723f35d79602b88ad50bc69f8d47d33101503e98c199a5be9f21.mp3", "archive_relative_path": "raw/audio/d75/d75d03a7cec7723f35d79602b88ad50bc69f8d47d33101503e98c199a5be9f21.mp3" } ] } ], "prediction": "Telo'tm na gmu'jg etlmisga'toq te's'g wela'gwe'g.", "reference": "Imtewnipete'get, nutaq newtitpa'q." }, { "id": "mic-sent-9534cb1ef9b0539cc2290eb7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I really like the sound of Native songs.", "output_text": "Nnueiei'l gtapegiaqann ni'n mawuls'tmann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I really like the sound of Native songs.", "mic_Latn": "Nnueiei'l gtapegiaqann ni'n mawuls'tmann." }, "canonical_ref": "entries/n/nnueiei/nnueiei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-742bfe310c16bf18842f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nnueiei/nnueiei.html", "entry_url": "https://mikmaqonline.org/entries/n/nnueiei/nnueiei.html", "headword": "nnueiei", "example_index": 0, "raw_html_path": "raw/entries/7142cea8eb8e49f51bbd8a3be7415af58d872d8d56915b8f038fb66f11cfd840.html", "raw_html_sha256": "d6b5f6672f096208d8ed1eda89a3667b2b41c20a3d86d991f52788fa81918f1f", "fetched_at": "2026-07-12T02:42:41.240Z", "recordings": [ { "recording_id": "a0a0e1cb23156a9a14a0cb29ba951c67339bd7180e8458f3419911ade5fb8dc2", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/441/4410552d7cdb3ca52e271e1b17013777e461ba91d71a8d4ae95fb1fc60e1dd94.mp3", "archive_relative_path": "raw/audio/441/4410552d7cdb3ca52e271e1b17013777e461ba91d71a8d4ae95fb1fc60e1dd94.mp3" } ] } ], "prediction": "Me' we'gwi'g ta'n tujiw Ntiewe'g.", "reference": "Nnueiei'l gtapegiaqann ni'n mawuls'tmann." }, { "id": "mic-sent-9547392bdf82e38986b1f1c6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The axe is headless, it just (in the immediate past) broke.", "output_text": "Tmi'gn temgwe'g, atel gis tltesg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The axe is headless, it just (in the immediate past) broke.", "mic_Latn": "Tmi'gn temgwe'g, atel gis tltesg." }, "canonical_ref": "entries/t/temgwe'g/temgwe'g.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ea89ad0e82f2d8fb24ef", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/temgwe'g/temgwe'g.html", "entry_url": "https://mikmaqonline.org/entries/t/temgwe'g/temgwe'g.html", "headword": "temgwe'g", "example_index": 1, "raw_html_path": "raw/entries/66b212d8be457d6f6b166dd5ddb471fda4a31a232b1186f6820c5e3160b9e7a5.html", "raw_html_sha256": "ca8097902067a9e69f15f35b3e7293bdab51d0e40ba490f9a487cebfaf221112", "fetched_at": "2026-07-12T02:45:37.626Z", "recordings": [ { "recording_id": "4880df0870b76a3afcbea8c53e480fac423541896a5a21d5517db9615f5d205e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5d1/5d1939596598836ca6e9ee0a1da4e591ee3a5f29fa5caa761d99da593026496e.mp3", "archive_relative_path": "raw/audio/5d1/5d1939596598836ca6e9ee0a1da4e591ee3a5f29fa5caa761d99da593026496e.mp3" } ] } ], "prediction": "Pugwelg na wi'gwig, pas'g gesatg.", "reference": "Tmi'gn temgwe'g, atel gis tltesg." }, { "id": "mic-sent-9606ea6e69cb735f2acb51cc:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It took along time for him/her to awaken him/her, he/she was so sleepy.", "output_text": "Pegije'g we'gawgis tugwipnnaj, teligtugsnnitl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It took along time for him/her to awaken him/her, he/she was so sleepy.", "mic_Latn": "Pegije'g we'gawgis tugwipnnaj, teligtugsnnitl." }, "canonical_ref": "entries/t/tugwipnnatl/tugwipnnatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5862bc75684696ba7134", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tugwipnnatl/tugwipnnatl.html", "entry_url": "https://mikmaqonline.org/entries/t/tugwipnnatl/tugwipnnatl.html", "headword": "tugwipnnatl", "example_index": 0, "raw_html_path": "raw/entries/e4afd4b074c10ec77fdc81b4fd731b01077191ae46d40a3fde09bce0649e17cb.html", "raw_html_sha256": "a797b8c1b05ad90c4e9a66fa738764b27e3ea4f1c723a6d69b587719221bce7e", "fetched_at": "2026-07-12T02:46:07.877Z", "recordings": [ { "recording_id": "cc5a44f5f0544368b443ca3f0d5b9958069164b1d3f7e60c4f68b24979bff485", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4cb/4cbb1d024c0f36c8999429dc4bd410164b44daf0b5405a4ac7fbc2570fdbceee.mp3", "archive_relative_path": "raw/audio/4cb/4cbb1d024c0f36c8999429dc4bd410164b44daf0b5405a4ac7fbc2570fdbceee.mp3" } ] } ], "prediction": "Te's gaqama'latl, telte'g.", "reference": "Pegije'g we'gawgis tugwipnnaj, teligtugsnnitl." }, { "id": "mic-sent-9656cd63c4f4b788e4604879:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary's glasses are new.", "output_text": "Mali ugpugugwe'l pile'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary's glasses are new.", "mic_Latn": "Mali ugpugugwe'l pile'l." }, "canonical_ref": "entries/u/ugpugugwe'l/ugpugugwe'l.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-476e4c1c85d32e4bc17a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugpugugwe'l/ugpugugwe'l.html", "entry_url": "https://mikmaqonline.org/entries/u/ugpugugwe'l/ugpugugwe'l.html", "headword": "ugpugugwe'l", "example_index": 0, "raw_html_path": "raw/entries/6fdec716f7c0851c9a02754e83b93572ada0d3f6659e7aa61407bed0d6a3bb69.html", "raw_html_sha256": "72e4e504521d0cdf3840b63c24cc56cd4da1da2a52adb4ae1754cd64fcc80b38", "fetched_at": "2026-07-12T02:46:14.209Z", "recordings": [ { "recording_id": "d5f650b875beedfaa01b9f9eac85692d0d89c55c7da175e4edbf331d9cb8f406", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/869/8690733db55b724968f850f34f0f765910c6f0eef4b1b558f0069e6644d01aa4.mp3", "archive_relative_path": "raw/audio/869/8690733db55b724968f850f34f0f765910c6f0eef4b1b558f0069e6644d01aa4.mp3" } ] } ], "prediction": "Mali's newte'g na gmu'j.", "reference": "Mali ugpugugwe'l pile'l." }, { "id": "mic-sent-96a1cad0e6bdfac0c0b2fc93:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When he/she was teasing him/her, he/she stuck his/her buttocks at him/her.", "output_text": "Etlgi'gassiteg eligjo'gmuatl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When he/she was teasing him/her, he/she stuck his/her buttocks at him/her.", "mic_Latn": "Etlgi'gassiteg eligjo'gmuatl." }, "canonical_ref": "entries/e/eligjo'gmuatl/eligjo'gmuatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-aa1219f2273e48ef1c4c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/eligjo'gmuatl/eligjo'gmuatl.html", "entry_url": "https://mikmaqonline.org/entries/e/eligjo'gmuatl/eligjo'gmuatl.html", "headword": "eligjo'gmuatl", "example_index": 0, "raw_html_path": "raw/entries/2594a4c5102e38d3f5b519840cfb372a450c2c8fa4ffb65c70e96e60a8214768.html", "raw_html_sha256": "319ada7343a253288f93dc1c1bef6ba31cda12dfa1a5da258629233f592c9ff9", "fetched_at": "2026-07-12T02:37:44.707Z", "recordings": [ { "recording_id": "f0d96221222e16279594113fd2ff16ae2c20a5f4e35e029ae770e29029e58f34", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/13c/13cabe59084913ea7103c33b4a3fd1affce374a0db0fb0e6f5de12b549b8ded8.mp3", "archive_relative_path": "raw/audio/13c/13cabe59084913ea7103c33b4a3fd1affce374a0db0fb0e6f5de12b549b8ded8.mp3" } ] } ], "prediction": "Ta'n tujiw etlmisga'latl, lpa ugta'qannl.", "reference": "Etlgi'gassiteg eligjo'gmuatl." }, { "id": "mic-sent-9753e16beef8ac48dd8a4638:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Did you buy a big blanket?", "output_text": "Mesgi'g a'su'n weja'tu's'p?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Did you buy a big blanket?", "mic_Latn": "Mesgi'g a'su'n weja'tu's'p?" }, "canonical_ref": "entries/a/a'su'n/a'su'n.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-59a5d32e36ee8c105f8e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/a'su'n/a'su'n.html", "entry_url": "https://mikmaqonline.org/entries/a/a'su'n/a'su'n.html", "headword": "a'su'n", "example_index": 0, "raw_html_path": "raw/entries/df1ced3443badc1bc2cfe6d892671a1b613c448868a7bea278588936ea9ea33e.html", "raw_html_sha256": "8cd9b6c8c32f062b80da87ba157a65e94dab3e5643df35f5de1db57d579b8f7e", "fetched_at": "2026-07-12T02:37:23.030Z", "recordings": [ { "recording_id": "4177eeebb30edbcb7d363a25fd177651e60082a16fe4e6b5c90a14888bdac5be", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/999/9994208f520648d6b4e0cc3da6cc119889eb498e9da0466626f877b86d7b9f4a.mp3", "archive_relative_path": "raw/audio/999/9994208f520648d6b4e0cc3da6cc119889eb498e9da0466626f877b86d7b9f4a.mp3" } ] } ], "prediction": "Gi's gi's'g na gmu'ji'j?", "reference": "Mesgi'g a'su'n weja'tu's'p?" }, { "id": "mic-sent-97936d28b6b49a1296945537:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The moon is very shiny.", "output_text": "Tepgunset na we'gwiwelaset.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The moon is very shiny.", "mic_Latn": "Tepgunset na we'gwiwelaset." }, "canonical_ref": "entries/w/welaset/welaset.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bce38e92261a186ea5a5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/welaset/welaset.html", "entry_url": "https://mikmaqonline.org/entries/w/welaset/welaset.html", "headword": "welaset", "example_index": 0, "raw_html_path": "raw/entries/3da3b6959e092ca829c5e944a9d83d493db7fa9e546f70a9349b1aacb74abcaf.html", "raw_html_sha256": "2c4f3cdb78bf80e3e0dd79aa9f33fd916ecd477d12da119027795bbd57750c09", "fetched_at": "2026-07-12T02:46:58.374Z", "recordings": [ { "recording_id": "b6abc86bc996a971d26807d948da2e921fe7e7c3c6a8cd6113c20d74005c6b46", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/418/4188499c421c758a9ba14d759e2f00af8fb3900c2e0db1ef4e03064874e193a1.mp3", "archive_relative_path": "raw/audio/418/4188499c421c758a9ba14d759e2f00af8fb3900c2e0db1ef4e03064874e193a1.mp3" } ] } ], "prediction": "We'gwi'g na wi'gatign.", "reference": "Tepgunset na we'gwiwelaset." }, { "id": "mic-sent-98160266da52950c7de9d22e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "We spilled all of the maple syrup.", "output_text": "Lpa gaqgutatestueg jioqsimusiapu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "We spilled all of the maple syrup.", "mic_Latn": "Lpa gaqgutatestueg jioqsimusiapu." }, "canonical_ref": "entries/g/gutatestoq/gutatestoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-520857fd3738551f3c4a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gutatestoq/gutatestoq.html", "entry_url": "https://mikmaqonline.org/entries/g/gutatestoq/gutatestoq.html", "headword": "gutatestoq", "example_index": 0, "raw_html_path": "raw/entries/a1f1fad32ff915f8f0f7f513fe5b51aad83a6fec847d40744927707e68a827c8.html", "raw_html_sha256": "fad73b0b5edef917cd262ee27e30a8c1f608f34cc8fcf1d5da6bb7696b861c18", "fetched_at": "2026-07-12T02:40:01.996Z", "recordings": [ { "recording_id": "1803c9cc7f5755e73ea0675e2ee54958192f791e36413085acf480460b2cc553", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dba/dba16f2454b84cc759e4014f3e268d44803d806d82288535d6bb5feecc5950da.mp3", "archive_relative_path": "raw/audio/dba/dba16f2454b84cc759e4014f3e268d44803d806d82288535d6bb5feecc5950da.mp3" } ] } ], "prediction": "Pugwelg'p't'p ms't wenji'guomg.", "reference": "Lpa gaqgutatestueg jioqsimusiapu." }, { "id": "mic-sent-983e0420bf97eec17e77945f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A very bad sickness can come from tobacco.", "output_text": "Maw winjig gsnugowaqan gisiwjiaq tmaweiigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A very bad sickness can come from tobacco.", "mic_Latn": "Maw winjig gsnugowaqan gisiwjiaq tmaweiigtug." }, "canonical_ref": "entries/m/maw_winjig/maw_winjig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-cf1a8ea954635ccec3c0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/maw_winjig/maw_winjig.html", "entry_url": "https://mikmaqonline.org/entries/m/maw_winjig/maw_winjig.html", "headword": "maw_winjig", "example_index": 0, "raw_html_path": "raw/entries/22e36adb914adc9a3a08d5d0ca94e192c0dcc7e2b0054f9159b72ca79976fb75.html", "raw_html_sha256": "92008c5107681d0660de4b1d1b08877635bcf6ad54988c4a147b18c01417d46d", "fetched_at": "2026-07-12T02:41:05.227Z", "recordings": [ { "recording_id": "e58db118661f61bd886ecc6d4cb802c7fb19cf555102a7b07a0258a1b8dc1bab", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/826/8266f0d3ed01bfda600827c8e7af940fe1926dd00f492d4e03071bc5ff28f705.mp3", "archive_relative_path": "raw/audio/826/8266f0d3ed01bfda600827c8e7af940fe1926dd00f492d4e03071bc5ff28f705.mp3" } ] } ], "prediction": "Pugwelg'g ta'n tujiw we'gwigtug.", "reference": "Maw winjig gsnugowaqan gisiwjiaq tmaweiigtug." }, { "id": "mic-sent-987fe79569d05fbaadaf5ee1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Hang that Mi'gmaq flag up high.", "output_text": "Esp'qapija'tu na Mi'gmewei mtawegn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Hang that Mi'gmaq flag up high.", "mic_Latn": "Esp'qapija'tu na Mi'gmewei mtawegn." }, "canonical_ref": "entries/m/mtawegn/mtawegn.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-01468d4c3562822d85f3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mtawegn/mtawegn.html", "entry_url": "https://mikmaqonline.org/entries/m/mtawegn/mtawegn.html", "headword": "mtawegn", "example_index": 0, "raw_html_path": "raw/entries/eec762d29f8d63c1311b72db244019b3aa743895ad59381f69f4eab74f794c21.html", "raw_html_sha256": "a66017a531716dbe65552dcf5df92fe1d73c926d3c71240ecbb360c18a30326e", "fetched_at": "2026-07-12T02:41:46.843Z", "recordings": [ { "recording_id": "421f67a4f9a840edce7ed7a178f1e0e357ec7117e8b0bb70b8e3243043c4d144", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0ed/0ed50225e32adf121f7649d56dafa5d5aa2a9e3429822224a62c2217be31b3ea.mp3", "archive_relative_path": "raw/audio/0ed/0ed50225e32adf121f7649d56dafa5d5aa2a9e3429822224a62c2217be31b3ea.mp3" } ] } ], "prediction": "Pugwelg na Mi'gme'g alapaqan.", "reference": "Esp'qapija'tu na Mi'gmewei mtawegn." }, { "id": "mic-sent-98976c5412558b76828df325:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Pack down everything well, it will be easier to handle.", "output_text": "Uliesna'tu ms't goqwei, me' nqamse'gt'tew ta'n telapjimg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Pack down everything well, it will be easier to handle.", "mic_Latn": "Uliesna'tu ms't goqwei, me' nqamse'gt'tew ta'n telapjimg." }, "canonical_ref": "entries/e/esna'toq/esna'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6549f6ecdca01048841a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/esna'toq/esna'toq.html", "entry_url": "https://mikmaqonline.org/entries/e/esna'toq/esna'toq.html", "headword": "esna'toq", "example_index": 0, "raw_html_path": "raw/entries/f345de9b240ca03e7acce8bb4913a3cdf79560f45c2548be4e3869336c9b78ea.html", "raw_html_sha256": "f6d3ce615c1e438958956d09698a079c5b02b2da5ac76024f0cd6d21dc5e4b4e", "fetched_at": "2026-07-12T02:38:17.468Z", "recordings": [ { "recording_id": "9ad257ba35462334ffdfd98f0896d27b7b88f83fb65a17da50270b0ed15db20e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/722/7225a27cceb4ced8182c0c5a97a840f4335e171ed4d98fa644c93968e1ec29f4.mp3", "archive_relative_path": "raw/audio/722/7225a27cceb4ced8182c0c5a97a840f4335e171ed4d98fa644c93968e1ec29f4.mp3" } ] } ], "prediction": "Ms't goqwei te's'g ta'n te'sipow, ms't we'gwas'g.", "reference": "Uliesna'tu ms't goqwei, me' nqamse'gt'tew ta'n telapjimg." }, { "id": "mic-sent-992b63f4994692a0478b7175:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Because (while) he/she looks persistently he/she sees what I see.", "output_text": "Ge's munsapitj na nemitoq ta'n goqwei ni'n nemitu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Because (while) he/she looks persistently he/she sees what I see.", "mic_Latn": "Ge's munsapitj na nemitoq ta'n goqwei ni'n nemitu." }, "canonical_ref": "entries/m/munsapit/munsapit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3b41bf0bb1b04057f106", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/munsapit/munsapit.html", "entry_url": "https://mikmaqonline.org/entries/m/munsapit/munsapit.html", "headword": "munsapit", "example_index": 0, "raw_html_path": "raw/entries/367d2f3d220c1e79d4c1e3c0b5520b9c04dcc371481b8c27d8850dbc905395f5.html", "raw_html_sha256": "d5ae7fca4409a377d0a5a73f70b9787893b82ceb2f8ef24d1d905b4148487719", "fetched_at": "2026-07-12T02:41:49.150Z", "recordings": [ { "recording_id": "f0d3fd3ede5741a2f468f9a4c0b8d37d7bd00529fd2cb0cbd1e7fbe542458fe7", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/28a/28a9286ddfc08f429bf3289700471a8d8486cc3c636d70eb66cd1959b034014b.mp3", "archive_relative_path": "raw/audio/28a/28a9286ddfc08f429bf3289700471a8d8486cc3c636d70eb66cd1959b034014b.mp3" } ] } ], "prediction": "Ta'n tujiw ta'n te'sijig nemia'toq.", "reference": "Ge's munsapitj na nemitoq ta'n goqwei ni'n nemitu." }, { "id": "mic-sent-99a028927cf36aa50cbbc750:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Would you help that man carrying a bed on his shoulder.", "output_text": "Ge' apoqnmu ala ji'nm mpo'qon pemn'gatg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Would you help that man carrying a bed on his shoulder.", "mic_Latn": "Ge' apoqnmu ala ji'nm mpo'qon pemn'gatg." }, "canonical_ref": "entries/p/pemn'gatg/pemn'gatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-191e24072268db5828d7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemn'gatg/pemn'gatg.html", "entry_url": "https://mikmaqonline.org/entries/p/pemn'gatg/pemn'gatg.html", "headword": "pemn'gatg", "example_index": 0, "raw_html_path": "raw/entries/38e2a8c41e186c326a00067ec6bdf1bd9baa3087b5488ed954d9a98e0b6a71b4.html", "raw_html_sha256": "b011a511ee5069a994b658a12c2fad85d765ec2b7645545334ce00d3df33b7fc", "fetched_at": "2026-07-12T02:43:35.221Z", "recordings": [ { "recording_id": "975684953674c8e4a4618c63c8a39087199abd2bcc616793668e65540037a68c", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/188/18881a3aa5234a10997bb3092584caff387931d8c11b909a82d3425a5ddba547.mp3", "archive_relative_path": "raw/audio/188/18881a3aa5234a10997bb3092584caff387931d8c11b909a82d3425a5ddba547.mp3" } ] } ], "prediction": "Ge' apoqwei na ji'nm elta'toq.", "reference": "Ge' apoqnmu ala ji'nm mpo'qon pemn'gatg." }, { "id": "mic-sent-99a26f3cabb6df35700be4ed:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Many people fast each spring time.", "output_text": "Pugwelg mimajuinu sune'wit te's siggw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Many people fast each spring time.", "mic_Latn": "Pugwelg mimajuinu sune'wit te's siggw." }, "canonical_ref": "entries/s/sune'wit/sune'wit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0d093404923983a2816f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sune'wit/sune'wit.html", "entry_url": "https://mikmaqonline.org/entries/s/sune'wit/sune'wit.html", "headword": "sune'wit", "example_index": 0, "raw_html_path": "raw/entries/9da6e98c269da3e2c1737bf765a42851c4f7028c4ccd1690bd96f07f78a335ff.html", "raw_html_sha256": "9f304b7359ff26ca0eca8bd85778c8f4844f01686abac7f17799793db21dd7b9", "fetched_at": "2026-07-12T02:45:17.519Z", "recordings": [ { "recording_id": "ba146ac2afc8011e2ddab2012b57cbaa7330c1f1df2d442bcf7cecac0b251441", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1a8/1a81439077ac49d9039aa69a28a85355e161112e88adb09caf4752ba91a87435.mp3", "archive_relative_path": "raw/audio/1a8/1a81439077ac49d9039aa69a28a85355e161112e88adb09caf4752ba91a87435.mp3" } ] } ], "prediction": "Pugwelg'p na ji'nm te's'g ta'n te'sipu'g.", "reference": "Pugwelg mimajuinu sune'wit te's siggw." }, { "id": "mic-sent-9a3445a68a22f2f4e5a0518d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "We're sad today, we weren't able to work.", "output_text": "Taqawajeieg gisgug, mu' gislugwewe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "We're sad today, we weren't able to work.", "mic_Latn": "Taqawajeieg gisgug, mu' gislugwewe'g." }, "canonical_ref": "entries/t/taqawaje'g/taqawaje'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-fb17fce0a840703d4086", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/taqawaje'g/taqawaje'g.html", "entry_url": "https://mikmaqonline.org/entries/t/taqawaje'g/taqawaje'g.html", "headword": "taqawaje'g", "example_index": 0, "raw_html_path": "raw/entries/ae8aac3f00fa576602b11d653241abf4135e7cf628bd9dbf0d3c32dab6281ee5.html", "raw_html_sha256": "287324878eca0ccd20c2d810b2dd393700e33a0309e2c8ab614e2d7ad83c3056", "fetched_at": "2026-07-12T02:45:25.177Z", "recordings": [ { "recording_id": "fe9116686f82a1e20fe4153c740173ca7373c6147e960ada2de736dc59d6e062", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d58/d58c292f00c38062312e20be248d299ab3291b480c2b772587121910939fd9be.mp3", "archive_relative_path": "raw/audio/d58/d58c292f00c38062312e20be248d299ab3291b480c2b772587121910939fd9be.mp3" } ] } ], "prediction": "Gisgug gisgug, mu getu'gug.", "reference": "Taqawajeieg gisgug, mu' gislugwewe'g." }, { "id": "mic-sent-9a5c9949f57927da80a7bd1d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she attaches it but it doesn't want to stick.", "output_text": "Megwasa'toq pas'g mu getu' megwasa's'tnug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she attaches it but it doesn't want to stick.", "mic_Latn": "Megwasa'toq pas'g mu getu' megwasa's'tnug." }, "canonical_ref": "entries/m/megwasa'toq/megwasa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ae8aa45288741e2344a3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/megwasa'toq/megwasa'toq.html", "entry_url": "https://mikmaqonline.org/entries/m/megwasa'toq/megwasa'toq.html", "headword": "megwasa'toq", "example_index": 0, "raw_html_path": "raw/entries/ab9416ea3d6a48a84c03b1e2472aedef99f340e218175f2122ddca739dfbf22e.html", "raw_html_sha256": "e684d513378c98bcf0f16fbf9933a385e851502c7d1448e75f310e334981b8f1", "fetched_at": "2026-07-12T02:41:09.145Z", "recordings": [ { "recording_id": "1dcaa275c56000a0ea831883b45c7083830c42b529879753b259d7366e798440", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e33/e331e7c3e33057ad3c42fa9530b413749dbc2701938ef248133393fc303ad1eb.mp3", "archive_relative_path": "raw/audio/e33/e331e7c3e33057ad3c42fa9530b413749dbc2701938ef248133393fc303ad1eb.mp3" } ] } ], "prediction": "Gesatg, gatu mu getu's'g.", "reference": "Megwasa'toq pas'g mu getu' megwasa's'tnug." }, { "id": "mic-sent-9b00cd978d5d003ab0e1d658:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My mother in law loves to pick berries.", "output_text": "Njugwi'jij gesatg mewisij ugjit glitaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My mother in law loves to pick berries.", "mic_Latn": "Njugwi'jij gesatg mewisij ugjit glitaq." }, "canonical_ref": "entries/m/mewisit/mewisit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-323cf9d4d9b360d6ee1d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mewisit/mewisit.html", "entry_url": "https://mikmaqonline.org/entries/m/mewisit/mewisit.html", "headword": "mewisit", "example_index": 0, "raw_html_path": "raw/entries/6bbd199b4fefef5d36d6c135cf518e55474b5e565fa3684c2de88b6be8bc2dbe.html", "raw_html_sha256": "1ec1250b5f4dc439c3570969348bd073b94aee6183505daef3bcf408df782b7a", "fetched_at": "2026-07-12T02:41:29.808Z", "recordings": [ { "recording_id": "e9aa5af2db2d20927b1ed74616fdc950127f6331efe39d8c08fb085f54e73206", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/792/792f15a7ccfbf82f85298f3eff224d7912b006fe36f84d52003a5dca26b6d4f3.mp3", "archive_relative_path": "raw/audio/792/792f15a7ccfbf82f85298f3eff224d7912b006fe36f84d52003a5dca26b6d4f3.mp3" } ] } ], "prediction": "Nuji'j gesgm'g gmu'j.", "reference": "Njugwi'jij gesatg mewisij ugjit glitaq." }, { "id": "mic-sent-9b762dceaa1362c1d0cbf7e3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You can say that a turtle is dome shaped.", "output_text": "Gis tluetes migjigj menjapsg'sit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You can say that a turtle is dome shaped.", "mic_Latn": "Gis tluetes migjigj menjapsg'sit." }, "canonical_ref": "entries/m/menjapsg'sit/menjapsg'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-afb17a627f2dd093e614", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/menjapsg'sit/menjapsg'sit.html", "entry_url": "https://mikmaqonline.org/entries/m/menjapsg'sit/menjapsg'sit.html", "headword": "menjapsg'sit", "example_index": 0, "raw_html_path": "raw/entries/6a2e9b9b3e7f9aa4857df2dd9acfdd4e0f69d6b2e3fa0ac6c285fec12f9b1cb2.html", "raw_html_sha256": "3f4a484543da7d677f336fe68defb80d08c082da9754ea858c810be33ed5f623", "fetched_at": "2026-07-12T02:41:17.407Z", "recordings": [ { "recording_id": "a471d612917705b679e85d25ea2678e838b32ad964d2f04b3985e94745c86faa", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/11b/11bf293ba886251f66251332088c152c52d117c11a2bdc4df49dc2240c29755a.mp3", "archive_relative_path": "raw/audio/11b/11bf293ba886251f66251332088c152c52d117c11a2bdc4df49dc2240c29755a.mp3" } ] } ], "prediction": "Gi's goqwei gmu'ji'j ta'n tujiw ugjit.", "reference": "Gis tluetes migjigj menjapsg'sit." }, { "id": "mic-sent-9b96d2dd1c1f8defdac9073e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My kid brother had sympathy pains while his first child was being born.", "output_text": "Ntjignam migultiap amgwesewe'l ugs'tqamuiniteg unjann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My kid brother had sympathy pains while his first child was being born.", "mic_Latn": "Ntjignam migultiap amgwesewe'l ugs'tqamuiniteg unjann." }, "canonical_ref": "entries/m/migultiat/migultiat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-12e6a29e0830fc171b07", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/migultiat/migultiat.html", "entry_url": "https://mikmaqonline.org/entries/m/migultiat/migultiat.html", "headword": "migultiat", "example_index": 0, "raw_html_path": "raw/entries/dda977813030934a79371222dded5cebd54a0c572aec3dbd8c5335077a6751e6.html", "raw_html_sha256": "3556fe33931b5807a9415614a4cf9ed9af74aeaa34b3632d5c017e0635b464ae", "fetched_at": "2026-07-12T02:41:33.630Z", "recordings": [ { "recording_id": "4aa6b34c47e98ec04ba0761c04c029705e710dbc692eadef548accec9d55d9a7", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cda/cda9d768f9467e8865c944794443cd9000117ccebb892fb7d2cf20d359855ed5.mp3", "archive_relative_path": "raw/audio/cda/cda9d768f9467e8865c944794443cd9000117ccebb892fb7d2cf20d359855ed5.mp3" } ] } ], "prediction": "Ntlamujig na'te's'g ta'n tujiw pas'g ugjit ugjit.", "reference": "Ntjignam migultiap amgwesewe'l ugs'tqamuiniteg unjann." }, { "id": "mic-sent-9bcd7a6134fca72d0862b1a0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My child is still dry.", "output_text": "Nnjan me' niwe'g", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My child is still dry.", "mic_Latn": "Nnjan me' niwe'g" }, "canonical_ref": "entries/n/niwe'g/niwe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e8d1b60c411acdb31a22", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/niwe'g/niwe'g.html", "entry_url": "https://mikmaqonline.org/entries/n/niwe'g/niwe'g.html", "headword": "niwe'g", "example_index": 0, "raw_html_path": "raw/entries/b978abe8272f334a167512a6bc3c5ce547ed9438b4d1be5b59c249ba756a3b9f.html", "raw_html_sha256": "6a635fbe8394cd7b0828765a5ee27ab9e1211326128c43dbd9ad4f16cf1ad7c6", "fetched_at": "2026-07-12T02:42:39.345Z", "recordings": [ { "recording_id": "107bc09a2e6e2484abb4e15f547dbbd4b674f052485b40f2e4cb6104e65aea12", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/258/258ff97fc39a2578447b9886699931e6d486e087257c6d883eeed6b109c53e8f.mp3", "archive_relative_path": "raw/audio/258/258ff97fc39a2578447b9886699931e6d486e087257c6d883eeed6b109c53e8f.mp3" } ] } ], "prediction": "Ngwis nige' na nmu'ji'j.", "reference": "Nnjan me' niwe'g" }, { "id": "mic-sent-9c8128602c1af2fdce7bbf12:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she dries the clothing outside.", "output_text": "Gujmug etlipiasg aligew.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she dries the clothing outside.", "mic_Latn": "Gujmug etlipiasg aligew." }, "canonical_ref": "entries/e/etlipiasg/etlipiasg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-860e819bcce804dfe710", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/etlipiasg/etlipiasg.html", "entry_url": "https://mikmaqonline.org/entries/e/etlipiasg/etlipiasg.html", "headword": "etlipiasg", "example_index": 0, "raw_html_path": "raw/entries/56e1fd5c8bdbde532fc241b94e86b1091fe659818ea6490287ba8e9adf563342.html", "raw_html_sha256": "115c3398f71a22ea664f1479def2620c1de33964a3ae819204ec7cfa82112288", "fetched_at": "2026-07-12T02:38:23.804Z", "recordings": [ { "recording_id": "6e2505447bad3cc2eeb113efeff240aef41702574bb83fb91433bc451684e557", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/178/178b4387ebff67b0dd11e97fa6624be16bd383909c71ec3d0ba72c70d617bcbc.mp3", "archive_relative_path": "raw/audio/178/178b4387ebff67b0dd11e97fa6624be16bd383909c71ec3d0ba72c70d617bcbc.mp3" } ] } ], "prediction": "Gaqama'latl ugjit.", "reference": "Gujmug etlipiasg aligew." }, { "id": "mic-sent-9ca9da45390633a4b05c2b7b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I'm looking for the cleanser.", "output_text": "Waqama'taqan algwilm.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I'm looking for the cleanser.", "mic_Latn": "Waqama'taqan algwilm." }, "canonical_ref": "entries/w/waqama'taqan/waqama'taqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bcc07a003b26c95dbedd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waqama'taqan/waqama'taqan.html", "entry_url": "https://mikmaqonline.org/entries/w/waqama'taqan/waqama'taqan.html", "headword": "waqama'taqan", "example_index": 0, "raw_html_path": "raw/entries/2a739d7c2f8445811da4a294be97cd3deb3d3a84b41acc4fc297b73b26e1efcf.html", "raw_html_sha256": "504b89ec3ba3e503f6a60bb9b1d0e02504cf3ee83c188433cca3a42a9eb51ac5", "fetched_at": "2026-07-12T02:46:37.111Z", "recordings": [ { "recording_id": "2cc4bab849c63ab547a58ff7503cc34d0591be5d48653b545a2c83f1307a5e3b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0a0/0a072b7fb98c5c831d34b32109895150d9d1848b4341594ff5eeef1b8ccfe266.mp3", "archive_relative_path": "raw/audio/0a0/0a072b7fb98c5c831d34b32109895150d9d1848b4341594ff5eeef1b8ccfe266.mp3" } ] } ], "prediction": "Ni'n etlmisga'toq.", "reference": "Waqama'taqan algwilm." }, { "id": "mic-sent-9cfb21eae329783f07ca3cd3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Look at that otter, s/he is floating along while eating.", "output_text": "Ge' angam ala giwnig, pemqo'get aq nespatalg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Look at that otter, s/he is floating along while eating.", "mic_Latn": "Ge' angam ala giwnig, pemqo'get aq nespatalg." }, "canonical_ref": "entries/p/pemqo'gwet/pemqo'gwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-22f2fb530dee4bdb945f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemqo'gwet/pemqo'gwet.html", "entry_url": "https://mikmaqonline.org/entries/p/pemqo'gwet/pemqo'gwet.html", "headword": "pemqo'gwet", "example_index": 0, "raw_html_path": "raw/entries/379584858a87404d8ade88dce85a8caa225ebb038a0a2e69e22f511c853d46f0.html", "raw_html_sha256": "cd8ee69cd6c7e25d621c4f604699d38b5cd2b744527fd6c8f42a430a330ab762", "fetched_at": "2026-07-12T02:43:36.237Z", "recordings": [ { "recording_id": "58ebbf5ab489e762b9da4bafde701bf0371de927801be82d25d1bd758a79b721", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/142/14230cefff4b457cfd79aa9852174661694e68a2ca4400ae48bf95636914e1a6.mp3", "archive_relative_path": "raw/audio/142/14230cefff4b457cfd79aa9852174661694e68a2ca4400ae48bf95636914e1a6.mp3" } ] } ], "prediction": "Ge' gisga'toq na nuta'q, gesatg ta'n te'siw.", "reference": "Ge' angam ala giwnig, pemqo'get aq nespatalg." }, { "id": "mic-sent-9d83e4bcfc59164ea968e28f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Joseph is leaving and taking all his belongs.", "output_text": "So'sep maja'sit aq poqtamga'toq ms't utapsun.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Joseph is leaving and taking all his belongs.", "mic_Latn": "So'sep maja'sit aq poqtamga'toq ms't utapsun." }, "canonical_ref": "entries/p/poqtamga'toq/poqtamga'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-131cff64df5de9736e43", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/poqtamga'toq/poqtamga'toq.html", "entry_url": "https://mikmaqonline.org/entries/p/poqtamga'toq/poqtamga'toq.html", "headword": "poqtamga'toq", "example_index": 0, "raw_html_path": "raw/entries/3b536ddb2931061c3447581fecba02d5d0a3b6724fd8e683ed1dcbfe9cfa9d60.html", "raw_html_sha256": "b815ccf7093d3de64f4c8143f0454a26a3f27ceebe520e92f3f1415b005c6820", "fetched_at": "2026-07-12T02:44:15.844Z", "recordings": [ { "recording_id": "5f75fffd1fbb75ebe63da7fcc3f09882edf6ec362ebfc4231268e024472fa74a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a17/a17218d84b6cf970338872e94d52639a42553c70017af7d602f21345c1979596.mp3", "archive_relative_path": "raw/audio/a17/a17218d84b6cf970338872e94d52639a42553c70017af7d602f21345c1979596.mp3" } ] } ], "prediction": "So'sep e'pite'g aq te's'g ta'n goqwei ugjit.", "reference": "So'sep maja'sit aq poqtamga'toq ms't utapsun." }, { "id": "mic-sent-9dc20b372b23bd2bb36800c8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My dog does alot of mischievous things, she must be closely watched.", "output_text": "Mawinta'mila'teget na nti, amujpa gigj'pugu'tut.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My dog does alot of mischievous things, she must be closely watched.", "mic_Latn": "Mawinta'mila'teget na nti, amujpa gigj'pugu'tut." }, "canonical_ref": "entries/m/mila'teget/mila'teget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-84ad26c22fa2bfbdaa30", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mila'teget/mila'teget.html", "entry_url": "https://mikmaqonline.org/entries/m/mila'teget/mila'teget.html", "headword": "mila'teget", "example_index": 0, "raw_html_path": "raw/entries/6184eac35762e8225556307c2f3bf091540b8c3a78d014cb91dad65930ff522b.html", "raw_html_sha256": "be932963b61564832774a2c758544b6251bf55bef14ab9f7a69f6113ee0b335f", "fetched_at": "2026-07-12T02:41:35.967Z", "recordings": [ { "recording_id": "476327baa5fbb13fe0094c72066226ec4bc488917e2760e932249a59319e57e0", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/695/695070b7fa26f0267d857ab6f382037c35a7bf35e97ef09b94f17d707d2a2273.mp3", "archive_relative_path": "raw/audio/695/695070b7fa26f0267d857ab6f382037c35a7bf35e97ef09b94f17d707d2a2273.mp3" } ] } ], "prediction": "Nmu'ji'j na wenji'guomg, amujpa mesgi'g.", "reference": "Mawinta'mila'teget na nti, amujpa gigj'pugu'tut." }, { "id": "mic-sent-9e5ac1321b206235aa6d3467:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I am getting old, every morning I must take pills.", "output_text": "Nugu'gisgu'wei, tesiegsitpu'g amujpa amawe'jitl wesua'tuann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I am getting old, every morning I must take pills.", "mic_Latn": "Nugu'gisgu'wei, tesiegsitpu'g amujpa amawe'jitl wesua'tuann." }, "canonical_ref": "entries/a/alawe'ji'j/alawe'ji'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3bbe75f73031cdfc1317", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/alawe'ji'j/alawe'ji'j.html", "entry_url": "https://mikmaqonline.org/entries/a/alawe'ji'j/alawe'ji'j.html", "headword": "alawe'ji'j", "example_index": 0, "raw_html_path": "raw/entries/50e703169fea2169c9ea7089f15e9b0fb8736a675ec6114524a8ae3317651982.html", "raw_html_sha256": "b26223b3417d3ab44096c041feba209baa4c7075d4b26f9f13e6089399c02e68", "fetched_at": "2026-07-12T02:36:38.921Z", "recordings": [ { "recording_id": "34a03bbb39a01081d6cd4e3823c943cb9a153ffb7dd0c631a980b4a1be8dc31c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/610/61030b59ed6c800a291347d592114712b54a11c899306b023f63719a87dbf178.mp3", "archive_relative_path": "raw/audio/610/61030b59ed6c800a291347d592114712b54a11c899306b023f63719a87dbf178.mp3" } ] } ], "prediction": "Gi's gesig, te'siegsitpu'g amujpa pilu'l.", "reference": "Nugu'gisgu'wei, tesiegsitpu'g amujpa amawe'jitl wesua'tuann." }, { "id": "mic-sent-9ea689cd0c75f87f77115e32:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That young woman is very attractive.", "output_text": "Ala gesite'wet e'pite's.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That young woman is very attractive.", "mic_Latn": "Ala gesite'wet e'pite's." }, "canonical_ref": "entries/g/gesite'wet/gesite'wet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ecedd6c6a9bf019db637", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesite'wet/gesite'wet.html", "entry_url": "https://mikmaqonline.org/entries/g/gesite'wet/gesite'wet.html", "headword": "gesite'wet", "example_index": 0, "raw_html_path": "raw/entries/9f1dd59eb191fd91b81604ad478129e6ad005cc951ee7de49f32a2fc52da5d92.html", "raw_html_sha256": "c609dd4cf12af8ce6a7a8557819d71e7334ac05077a5a197e3f562b683a087d6", "fetched_at": "2026-07-12T02:39:14.751Z", "recordings": [ { "recording_id": "bc09b0087b88ef2aea88976475e34d07868dd29a190c1632580fc70c6c294443", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1ae/1ae2ad82f67167ce8040efa5c2e83dd49bb2ccb36c98f312f27155bc3a9f143d.mp3", "archive_relative_path": "raw/audio/1ae/1ae2ad82f67167ce8040efa5c2e83dd49bb2ccb36c98f312f27155bc3a9f143d.mp3" } ] } ], "prediction": "Na we'ji'jg na ji'nm.", "reference": "Ala gesite'wet e'pite's." }, { "id": "mic-sent-9fa6f9c2edb212b0200972a3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The baby just bit his/her mother's breast.", "output_text": "Mijua'ji'j gisipqa'tuatl uggwijl ugmlagejml.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The baby just bit his/her mother's breast.", "mic_Latn": "Mijua'ji'j gisipqa'tuatl uggwijl ugmlagejml." }, "canonical_ref": "entries/u/ugmlagejml/ugmlagejml.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5ac070db59f3f9db0371", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugmlagejml/ugmlagejml.html", "entry_url": "https://mikmaqonline.org/entries/u/ugmlagejml/ugmlagejml.html", "headword": "ugmlagejml", "example_index": 0, "raw_html_path": "raw/entries/b20ae0d4c1a9e512b7777604241a294268a69f0126fa0cd1b2aa4ae8a09d47b3.html", "raw_html_sha256": "0a2c375415668c082b7ebf73c761731737f0aff65264b91d243f55791ef03b78", "fetched_at": "2026-07-12T02:46:12.700Z", "recordings": [ { "recording_id": "9ca00a9797bf14c0476016d308d22a438896d69c66879b571fcd74dae9f9add0", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/855/8555322a5081347898f4048e6abaa2131f92cdab3ed19af3e2ab4f9966da5c40.mp3", "archive_relative_path": "raw/audio/855/8555322a5081347898f4048e6abaa2131f92cdab3ed19af3e2ab4f9966da5c40.mp3" } ] } ], "prediction": "Lpa'tu'ji'j pas'g gesgmnaq ugjitl ugti'l.", "reference": "Mijua'ji'j gisipqa'tuatl uggwijl ugmlagejml." }, { "id": "mic-sent-9fbde75831ed24ff76cdf7bb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The priest is wears scapular.", "output_text": "Etu'gutewe'l pa'tlia's nasguatl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The priest is wears scapular.", "mic_Latn": "Etu'gutewe'l pa'tlia's nasguatl." }, "canonical_ref": "entries/n/nasguatl/nasguatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ec018d1da411167a4451", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nasguatl/nasguatl.html", "entry_url": "https://mikmaqonline.org/entries/n/nasguatl/nasguatl.html", "headword": "nasguatl", "example_index": 0, "raw_html_path": "raw/entries/a942cbff5329ab1b92f9b43d0695c4edaf4a5a43bb8445ac6ab54e1f80041915.html", "raw_html_sha256": "bc6cb6d95555246259ab1824a22c7791eb44f5bb740222af2243005b7410f6f6", "fetched_at": "2026-07-12T02:42:07.353Z", "recordings": [ { "recording_id": "a89d6bfff9afd0a00b7f44bcaf91571ff0b26247f00a0914f071949517931846", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/658/65840803fdf62cfb90cfcb7ac630eeefc9f6e63f0aeb5e9e03f91346059036a0.mp3", "archive_relative_path": "raw/audio/658/65840803fdf62cfb90cfcb7ac630eeefc9f6e63f0aeb5e9e03f91346059036a0.mp3" } ] } ], "prediction": "Pa'tu'ji'j etlmisga'toq.", "reference": "Etu'gutewe'l pa'tlia's nasguatl." }, { "id": "mic-sent-9ffa511da5afaca7da8c7283:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I have often been to New Brunswick.", "output_text": "Gi's gaqi'sg wejiei Signigtewa'gig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I have often been to New Brunswick.", "mic_Latn": "Gi's gaqi'sg wejiei Signigtewa'gig." }, "canonical_ref": "entries/s/Signigtewa'gi/Signigtewa'gi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c06e6150bb102b9ed2dd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/Signigtewa'gi/Signigtewa'gi.html", "entry_url": "https://mikmaqonline.org/entries/s/Signigtewa'gi/Signigtewa'gi.html", "headword": "Signigtewa'gi", "example_index": 0, "raw_html_path": "raw/entries/59e412cc5504a459cf6e8392768f50ca71dac56547c9f5ffb6840e49117e61d9.html", "raw_html_sha256": "60fec631ebb74940a0dd92be5dd02760ca23278ae132cfeaa953f034577e3f50", "fetched_at": "2026-07-12T02:45:00.539Z", "recordings": [ { "recording_id": "124e8a7150d5ae1a5e5bb6348fefcc29c45d0f9e3d6dc921640ecb7445387ab5", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cfd/cfd149132b0ee0cb9ae043a7a4321359ac7f196ee0d2a22201312a2bf2973413.mp3", "archive_relative_path": "raw/audio/cfd/cfd149132b0ee0cb9ae043a7a4321359ac7f196ee0d2a22201312a2bf2973413.mp3" } ] } ], "prediction": "Gi's gi's nige' New Brunswi'g.", "reference": "Gi's gaqi'sg wejiei Signigtewa'gig." }, { "id": "mic-sent-a02424e8a0b0067243da8b50:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "His/her house is fancy.", "output_text": "Asamatteg wi'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "His/her house is fancy.", "mic_Latn": "Asamatteg wi'g." }, "canonical_ref": "entries/a/asamatteg/asamatteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-89e53d46c621173738fe", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/asamatteg/asamatteg.html", "entry_url": "https://mikmaqonline.org/entries/a/asamatteg/asamatteg.html", "headword": "asamatteg", "example_index": 0, "raw_html_path": "raw/entries/5ed5356c03bbabd3903bc7dda92813767d4db8b7f3456f7971bffd6796f1f8c2.html", "raw_html_sha256": "b767e03868042d099a61947183c0998ef6651e9c039c6c66994d5e05a971df41", "fetched_at": "2026-07-12T02:37:18.612Z", "recordings": [ { "recording_id": "aff0c82d54c4b8785b70f0262a68b415903f1ce765fbdb21d98d2c603551fdb2", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c1b/c1b7ef5279daa0d42c8d79b0569a06d0b2e67ca1aeffceb82499c09e1ead40c6.mp3", "archive_relative_path": "raw/audio/c1b/c1b7ef5279daa0d42c8d79b0569a06d0b2e67ca1aeffceb82499c09e1ead40c6.mp3" } ] } ], "prediction": "We'gwi'g na ugjit.", "reference": "Asamatteg wi'g." }, { "id": "mic-sent-a08c16761a25d94597b73870:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little girl has lost her shoe.", "output_text": "E'pite'ji'j umugsnn gisie'natl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little girl has lost her shoe.", "mic_Latn": "E'pite'ji'j umugsnn gisie'natl." }, "canonical_ref": "entries/u/umugsnn/umugsnn.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8841c49babd272a837b8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/umugsnn/umugsnn.html", "entry_url": "https://mikmaqonline.org/entries/u/umugsnn/umugsnn.html", "headword": "umugsnn", "example_index": 0, "raw_html_path": "raw/entries/c4919ca4c7da997ea0d21e8d8d54cdada1db35bb1e4b575135d496c0c2292509.html", "raw_html_sha256": "19cef4d564612eab2baf83dade3acec0170bcf8cc31e243660857d43edce94b3", "fetched_at": "2026-07-12T02:46:24.956Z", "recordings": [ { "recording_id": "d7aa553fd8c53d070644eadeaa2325dd6a1245f4be4c0505d4c44e3964d59df6", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5d1/5d1c9f56787a193334a9a45eca265a054d5884dedce6532e43a8569eef4be475.mp3", "archive_relative_path": "raw/audio/5d1/5d1c9f56787a193334a9a45eca265a054d5884dedce6532e43a8569eef4be475.mp3" } ] } ], "prediction": "E'pite'ji'j gesatg ugjit.", "reference": "E'pite'ji'j umugsnn gisie'natl." }, { "id": "mic-sent-a104a81846e3f446605d00ef:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I really like the sound of Native songs.", "output_text": "Lnueiei'l gtapegiaqann ni'n maw(i) uls'tmann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I really like the sound of Native songs.", "mic_Latn": "Lnueiei'l gtapegiaqann ni'n maw(i) uls'tmann." }, "canonical_ref": "entries/l/lnueiei/lnueiei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-742bfe310c16bf18842f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lnueiei/lnueiei.html", "entry_url": "https://mikmaqonline.org/entries/l/lnueiei/lnueiei.html", "headword": "lnueiei", "example_index": 0, "raw_html_path": "raw/entries/cc51c3f46d5d7c8fa4a4d6da347c4447768b56faf1d2db6f3df42f034d580e41.html", "raw_html_sha256": "5faceb48be7f5a05b885f7ee0e43119e2b639b1e1586328efda5f0d5d9f644dd", "fetched_at": "2026-07-12T02:40:36.700Z", "recordings": [ { "recording_id": "d6ff70a8b7962b6284cba927c9159c3718ab0b62d488e0402b4a021aba8ba300", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/441/4410552d7cdb3ca52e271e1b17013777e461ba91d71a8d4ae95fb1fc60e1dd94.mp3", "archive_relative_path": "raw/audio/441/4410552d7cdb3ca52e271e1b17013777e461ba91d71a8d4ae95fb1fc60e1dd94.mp3" } ] } ], "prediction": "Me' we'gwi'g ta'n tujiw Ntiewe'g.", "reference": "Lnueiei'l gtapegiaqann ni'n maw(i) uls'tmann." }, { "id": "mic-sent-a15cf5eebc3fa3b1ed163e1f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It seems stove is doing poorly, I'll stoke the fire.", "output_text": "Teleiaq mala'sit ula epsaqtejg, ge' iljoqte'g'p.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It seems stove is doing poorly, I'll stoke the fire.", "mic_Latn": "Teleiaq mala'sit ula epsaqtejg, ge' iljoqte'g'p." }, "canonical_ref": "entries/m/mala'sit/mala'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c7e156328e286f61cdfc", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mala'sit/mala'sit.html", "entry_url": "https://mikmaqonline.org/entries/m/mala'sit/mala'sit.html", "headword": "mala'sit", "example_index": 0, "raw_html_path": "raw/entries/9142da32252a5d324760842a73b972f70b8a49ba8f6215e4eb49009ee48bfacf.html", "raw_html_sha256": "87b758ca3b2e7a9a5af05943415b922648dfd6cd9e8437eb2f2bf836df756967", "fetched_at": "2026-07-12T02:40:43.026Z", "recordings": [ { "recording_id": "d8cbee9c605dff22bb5ac2358f7f8ec02b319c444ecbc27739d0ce7f81171d0d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b2a/b2a2ec4299313317bd96b3542c16c0ba9e28f4a44bd8c9f11f91164c2367c75f.mp3", "archive_relative_path": "raw/audio/b2a/b2a2ec4299313317bd96b3542c16c0ba9e28f4a44bd8c9f11f91164c2367c75f.mp3" } ] } ], "prediction": "Me' gesatg na gmu'j, wesamg'p'te'l.", "reference": "Teleiaq mala'sit ula epsaqtejg, ge' iljoqte'g'p." }, { "id": "mic-sent-a23dbc454e0cc6682b47a8b0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My grandfather told me a story last night.", "output_text": "Nmijgamij a'tugwewip wela'gwe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My grandfather told me a story last night.", "mic_Latn": "Nmijgamij a'tugwewip wela'gwe'g." }, "canonical_ref": "entries/a/a'tugwewatl/a'tugwewatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-333dae3cc9093356904a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/a'tugwewatl/a'tugwewatl.html", "entry_url": "https://mikmaqonline.org/entries/a/a'tugwewatl/a'tugwewatl.html", "headword": "a'tugwewatl", "example_index": 0, "raw_html_path": "raw/entries/39bd62f2fbadc3b55ec44ed23af4604d11adec8adc2a79319e2b73c95ac87a80.html", "raw_html_sha256": "6ff6a19711c0a23614a27db8089025f137551a86a97f2e3345bcda566b301c6f", "fetched_at": "2026-07-12T02:37:27.463Z", "recordings": [ { "recording_id": "27020279ece8b8d11c2d123c538e8d40b0deb80f4064748d01777feb00fceaef", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/26c/26c7a6bcd9057821103462f6bcc28c574e73eb6ee3e7fb94dda2743516381b37.mp3", "archive_relative_path": "raw/audio/26c/26c7a6bcd9057821103462f6bcc28c574e73eb6ee3e7fb94dda2743516381b37.mp3" } ] } ], "prediction": "Nuji'j telta'latl ugjit wela'gwe'g.", "reference": "Nmijgamij a'tugwewip wela'gwe'g." }, { "id": "mic-sent-a2724343facc8a51b28b04d3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The lid is stuck, he/she has to cut the bucket open.", "output_text": "Amjimoqteg pgijoqign, amujpa pansatl na la'taqsunn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The lid is stuck, he/she has to cut the bucket open.", "mic_Latn": "Amjimoqteg pgijoqign, amujpa pansatl na la'taqsunn." }, "canonical_ref": "entries/p/pansatl/pansatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bb4b3b128c2d39b2eb37", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pansatl/pansatl.html", "entry_url": "https://mikmaqonline.org/entries/p/pansatl/pansatl.html", "headword": "pansatl", "example_index": 0, "raw_html_path": "raw/entries/56124eb7acf897b66a99fb6cd78229d3386d3b5748d6b67d87717ee54ec3e0de.html", "raw_html_sha256": "be60bef93dbef57088384ae514cea614053879def2c3585c6872110eed138c23", "fetched_at": "2026-07-12T02:43:06.686Z", "recordings": [ { "recording_id": "2f359e67be88c283986f1b2b18542e346054b6073dc149c948611704447c6e2a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/338/33806f6eb02a3b7b0995e19d265876e0b7fc3033f26e22e90c322876f8cb5bfc.mp3", "archive_relative_path": "raw/audio/338/33806f6eb02a3b7b0995e19d265876e0b7fc3033f26e22e90c322876f8cb5bfc.mp3" } ] } ], "prediction": "Pilei, amujpa amgwesga'toq ugta'qann.", "reference": "Amjimoqteg pgijoqign, amujpa pansatl na la'taqsunn." }, { "id": "mic-sent-a292adbbfefaaf15508698c7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The boat pole is (lays on top) over there.", "output_text": "Gi'gamgo'n ala' tett ge'goqpit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The boat pole is (lays on top) over there.", "mic_Latn": "Gi'gamgo'n ala' tett ge'goqpit." }, "canonical_ref": "entries/g/ge'goqpit/ge'goqpit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6d11c16991642356739e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/ge'goqpit/ge'goqpit.html", "entry_url": "https://mikmaqonline.org/entries/g/ge'goqpit/ge'goqpit.html", "headword": "ge'goqpit", "example_index": 0, "raw_html_path": "raw/entries/826631485ceb67f189aac4d42b157a8a0cc858738ace04a70425d6f6d8f2fcea.html", "raw_html_sha256": "7cbc9c8caabb2c31f30f705da8651838ad267ed00b75fe4b6979253a32d45f8a", "fetched_at": "2026-07-12T02:38:50.951Z", "recordings": [ { "recording_id": "7b9c4cb07f1a860fc089626feec7351fb374d33b8345fb44f1fc45ad31047ef1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4cc/4cc590ad7ec3a6b8e0dfdb67dc9200208cad4c1aa0ea799fec545874fff14a42.mp3", "archive_relative_path": "raw/audio/4cc/4cc590ad7ec3a6b8e0dfdb67dc9200208cad4c1aa0ea799fec545874fff14a42.mp3" } ] } ], "prediction": "Lpa wi'gwi'g na ala.", "reference": "Gi'gamgo'n ala' tett ge'goqpit." }, { "id": "mic-sent-a2eb2bd72f86496df2a07fda:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "First he/she folds his/her money and then he/she pockets it.", "output_text": "Na tmg ilanqa'toq ugtsulieweim toqosi'p maposa'toq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "First he/she folds his/her money and then he/she pockets it.", "mic_Latn": "Na tmg ilanqa'toq ugtsulieweim toqosi'p maposa'toq." }, "canonical_ref": "entries/i/ilanqa'toq/ilanqa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d4c295fc2ba262964df1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/ilanqa'toq/ilanqa'toq.html", "entry_url": "https://mikmaqonline.org/entries/i/ilanqa'toq/ilanqa'toq.html", "headword": "ilanqa'toq", "example_index": 0, "raw_html_path": "raw/entries/6cdebdec781c4bac5806f8fd9846025be3817f1c53b581b655a8d31de2eef5d9.html", "raw_html_sha256": "ebd0a84f8595bd38762849bd624f8ca8c78a59cb29a8d8e1d828c446ba8dfbf0", "fetched_at": "2026-07-12T02:40:06.945Z", "recordings": [ { "recording_id": "f938dac443800b6d4c800875e300bd61ff766feb0dd9775dc3b9cbadd45e4d0b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7d6/7d65a3bd2931793ed58c4e9146a873d8223192a9109d23b832cbe9b2ce7ddbbd.mp3", "archive_relative_path": "raw/audio/7d6/7d65a3bd2931793ed58c4e9146a873d8223192a9109d23b832cbe9b2ce7ddbbd.mp3" } ] } ], "prediction": "Tami gesatg ugta'latl ugjit aq pas'g na'te'l.", "reference": "Na tmg ilanqa'toq ugtsulieweim toqosi'p maposa'toq." }, { "id": "mic-sent-a2fa24c99931ee9803b28b6a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The patient is suffering.", "output_text": "Gsnugowinu welmaje'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The patient is suffering.", "mic_Latn": "Gsnugowinu welmaje'g." }, "canonical_ref": "entries/w/welmaje'g/welmaje'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8c2bf5425c73da1352ef", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/welmaje'g/welmaje'g.html", "entry_url": "https://mikmaqonline.org/entries/w/welmaje'g/welmaje'g.html", "headword": "welmaje'g", "example_index": 0, "raw_html_path": "raw/entries/dbcece5429b7fbaf658f73e65347f0698878e6ae5ffc4e0e1a2ff88974649c5e.html", "raw_html_sha256": "9d05b7bafdb60ce3389f4a05d54a2609a857f8892e392cf0d215b4237cf970d1", "fetched_at": "2026-07-12T02:47:05.605Z", "recordings": [ { "recording_id": "9abd704051c9c294699a2eb8ab6bb94f1d17742cc957cb701c155fcdf69b362a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9e3/9e34b1cb8369b7c42901c1bea852c65d3a81dce5dbf2416e22a7fb06ab8558bd.mp3", "archive_relative_path": "raw/audio/9e3/9e34b1cb8369b7c42901c1bea852c65d3a81dce5dbf2416e22a7fb06ab8558bd.mp3" } ] } ], "prediction": "Gisigu's'g na lpa ms't.", "reference": "Gsnugowinu welmaje'g." }, { "id": "mic-sent-a39a1272dbd8b89cf7e19a8e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "These candies are too sweet for me.", "output_text": "Wesamseggul ula suitisl ugjit ni'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "These candies are too sweet for me.", "mic_Latn": "Wesamseggul ula suitisl ugjit ni'n." }, "canonical_ref": "entries/s/seggw/seggw.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7bfa4d62f22832652e27", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/seggw/seggw.html", "entry_url": "https://mikmaqonline.org/entries/s/seggw/seggw.html", "headword": "seggw", "example_index": 1, "raw_html_path": "raw/entries/fe8a4ea07737eba6d9c561c1818b709f085bacba5cee0ef69a682e49ea544342.html", "raw_html_sha256": "d94813acd41b1a55332979f3820742a1761aecc800a5fae700ef9879fa485cbc", "fetched_at": "2026-07-12T02:44:48.083Z", "recordings": [ { "recording_id": "5f3f418cfe13d59a04069c1bcebc731a0a89e8b36b9d31d6c1dd10d5d3d586cc", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a40/a4089483c10d386552cd0dc2bbf5d3da3e6e1081efc9307cf8f8ae820c2fa359.mp3", "archive_relative_path": "raw/audio/a40/a4089483c10d386552cd0dc2bbf5d3da3e6e1081efc9307cf8f8ae820c2fa359.mp3" } ] } ], "prediction": "We'gwi'g na ula gmu'ji'j.", "reference": "Wesamseggul ula suitisl ugjit ni'n." }, { "id": "mic-sent-a3f4c5c2e1afa80cb25ed62b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I like a silk blouse.", "output_text": "Ni'n gesalg lapli'signei matlet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I like a silk blouse.", "mic_Latn": "Ni'n gesalg lapli'signei matlet." }, "canonical_ref": "entries/l/lapli'sign/lapli'sign.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-08c871dca3ec38071d21", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lapli'sign/lapli'sign.html", "entry_url": "https://mikmaqonline.org/entries/l/lapli'sign/lapli'sign.html", "headword": "lapli'sign", "example_index": 0, "raw_html_path": "raw/entries/8558f4e55b2c9252d98ede84335a1e3b589a7f16529302b8e5941c75f8a2f2c1.html", "raw_html_sha256": "5cfb9625ac679be5be0f8d9767d7f59003592bbfb2799374b0f44b872081c415", "fetched_at": "2026-07-12T02:40:30.368Z", "recordings": [ { "recording_id": "348ac10950f93e67226e7777e57f12aa647600308646ce345ae836d71ff214fb", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/76b/76b20a849e8ddf2599d6c674758f9d3c3387f6cf8e4876861d76b5e59708ec49.mp3", "archive_relative_path": "raw/audio/76b/76b20a849e8ddf2599d6c674758f9d3c3387f6cf8e4876861d76b5e59708ec49.mp3" } ] } ], "prediction": "Pilei ni'n gmu'ji'j.", "reference": "Ni'n gesalg lapli'signei matlet." }, { "id": "mic-sent-a423fbf3e5bc1fd66e0c84ff:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's very dangerous when the road is icy.", "output_text": "Mawinsanoqon na ta'n tujiw mgumi'gnig awti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's very dangerous when the road is icy.", "mic_Latn": "Mawinsanoqon na ta'n tujiw mgumi'gnig awti." }, "canonical_ref": "entries/m/mgumi'gnig/mgumi'gnig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4bca3bad16b43c42fdd6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mgumi'gnig/mgumi'gnig.html", "entry_url": "https://mikmaqonline.org/entries/m/mgumi'gnig/mgumi'gnig.html", "headword": "mgumi'gnig", "example_index": 0, "raw_html_path": "raw/entries/e8cf4631588a3b6274f1828f0de4e7e2d82ac8954fd431465fafd9773f348005.html", "raw_html_sha256": "4b28cf73a667fa064ef03cf12f0dfee4e7bdd342730d1435854038448e282b09", "fetched_at": "2026-07-12T02:41:32.040Z", "recordings": [ { "recording_id": "70d0fdf53ecd231d07a165e8996a06aa6fd5b51e0c865158b30c78100009179a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d4b/d4bc4281394451d7fee280fb0198d30dd880a0c8266852a9dc483a470a9f95a5.mp3", "archive_relative_path": "raw/audio/d4b/d4bc4281394451d7fee280fb0198d30dd880a0c8266852a9dc483a470a9f95a5.mp3" } ] } ], "prediction": "Me' pugwelg ta'n tujiw gesgm'g.", "reference": "Mawinsanoqon na ta'n tujiw mgumi'gnig awti." }, { "id": "mic-sent-a45be35ecdab9d8ca15fd294:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little boy is working hard to empty out the barrel, using a pint dipper.", "output_text": "Lpa'tu'ji'j gina'sit malige'wl niwa'latl, etlwe'watl suppinn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little boy is working hard to empty out the barrel, using a pint dipper.", "mic_Latn": "Lpa'tu'ji'j gina'sit malige'wl niwa'latl, etlwe'watl suppinn." }, "canonical_ref": "entries/n/niwa'latl/niwa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3fc548d34728498424b8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/niwa'latl/niwa'latl.html", "entry_url": "https://mikmaqonline.org/entries/n/niwa'latl/niwa'latl.html", "headword": "niwa'latl", "example_index": 0, "raw_html_path": "raw/entries/c7461f6913ce75a6fcbfa48ba7bc1e87db18e29faf4a19322c06d1b7ce8a9a32.html", "raw_html_sha256": "c632ef7aeea45b976be9043d6ea4cbb1d6e2d4954181456ab9eb25e21febaf14", "fetched_at": "2026-07-12T02:42:38.943Z", "recordings": [ { "recording_id": "3ec581b43756f9b9112bcacb50aae4e64fbaf644e71cc142cdfff951e836b322", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/358/358e9fd74e42375e2035d0fa4dc254f6e101c960a99e624ffba39e3ac4a551a1.mp3", "archive_relative_path": "raw/audio/358/358e9fd74e42375e2035d0fa4dc254f6e101c960a99e624ffba39e3ac4a551a1.mp3" } ] } ], "prediction": "Lpa'tu'ji'j gesgm't'g lpa'qann, lpa gmu'j.", "reference": "Lpa'tu'ji'j gina'sit malige'wl niwa'latl, etlwe'watl suppinn." }, { "id": "mic-sent-a4d23090af590636088866aa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "One of my friends has plenty of money, we'll ask him/her.", "output_text": "Newte'jit nitap megeng suliewei, negm glutmuatesnu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "One of my friends has plenty of money, we'll ask him/her.", "mic_Latn": "Newte'jit nitap megeng suliewei, negm glutmuatesnu." }, "canonical_ref": "entries/m/megeng/megeng.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e09fba002c37eaf5bb76", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/megeng/megeng.html", "entry_url": "https://mikmaqonline.org/entries/m/megeng/megeng.html", "headword": "megeng", "example_index": 0, "raw_html_path": "raw/entries/dfe39c6e5914eefa1b78f2497d2bb917414a39b0ea82220ee7fc171f3496eeb4.html", "raw_html_sha256": "8d5ddb1cccbd62e8ea0165521425600cb2671fc8493aec962cd79f13bc26cbe3", "fetched_at": "2026-07-12T02:41:06.048Z", "recordings": [ { "recording_id": "47f137dd08848aebee0e9e950378585e7bed475ad923765575c9ac28686153cc", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/00d/00d0d9e4fc968dc9a02db1d96f3a9fa31d477e6fe9fab5653a252afa8d41061e.mp3", "archive_relative_path": "raw/audio/00d/00d0d9e4fc968dc9a02db1d96f3a9fa31d477e6fe9fab5653a252afa8d41061e.mp3" } ] } ], "prediction": "Amujpa nitap na mawjitujig, amujpa'tu'n.", "reference": "Newte'jit nitap megeng suliewei, negm glutmuatesnu." }, { "id": "mic-sent-a4e0e505821311bb100b5d46:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I've made a potato basket.", "output_text": "Ni'n gisitu tapatanei ligpenign.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I've made a potato basket.", "mic_Latn": "Ni'n gisitu tapatanei ligpenign." }, "canonical_ref": "entries/l/ligpenign/ligpenign.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-78a88d5085d8855fd0bd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/ligpenign/ligpenign.html", "entry_url": "https://mikmaqonline.org/entries/l/ligpenign/ligpenign.html", "headword": "ligpenign", "example_index": 0, "raw_html_path": "raw/entries/9f57b50fc61b8e8db3e66d5840b2de81928d9f679659da048c97504958e57316.html", "raw_html_sha256": "865b06dd0e6fb64443bf8a44e461cdd01c234b0a99475dd24dd5730183de993d", "fetched_at": "2026-07-12T02:40:34.593Z", "recordings": [ { "recording_id": "81f7bb178f570ffd2637e63002dc5390c6a78703dbd28ce133f3169d22e46a31", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7cd/7cdb5c4d35673369841f7fb9e692bef133ad16041308168d378b9533cee0e3d4.mp3", "archive_relative_path": "raw/audio/7cd/7cdb5c4d35673369841f7fb9e692bef133ad16041308168d378b9533cee0e3d4.mp3" } ] } ], "prediction": "Pugwelg'p na p'te's'g.", "reference": "Ni'n gisitu tapatanei ligpenign." }, { "id": "mic-sent-a4f68b1d60919ff734446788:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is getting prepared because tomorrow he/she is leaving.", "output_text": "Gisgug ilajit muta sapo'nug maja'sit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is getting prepared because tomorrow he/she is leaving.", "mic_Latn": "Gisgug ilajit muta sapo'nug maja'sit." }, "canonical_ref": "entries/i/ilajit/ilajit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c905869fea45eceff8a8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/ilajit/ilajit.html", "entry_url": "https://mikmaqonline.org/entries/i/ilajit/ilajit.html", "headword": "ilajit", "example_index": 0, "raw_html_path": "raw/entries/160f0879515b957edb53df35737971d6b061a271c9756fb5fdda89ec64afd3c4.html", "raw_html_sha256": "accbe50d4199c652f018fa80cbac7b55c9051094eeb0ef6794bfa16b6b288c92", "fetched_at": "2026-07-12T02:40:06.126Z", "recordings": [ { "recording_id": "0cb0f1884e70d6c6cd231b13bd99f205e1cd2b4f1df4447ac4270f0ef35969d2", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4b8/4b8ca3db50929987ee414919cd0800def8408b7ce3294be76c33ba65491b1b20.mp3", "archive_relative_path": "raw/audio/4b8/4b8ca3db50929987ee414919cd0800def8408b7ce3294be76c33ba65491b1b20.mp3" } ] } ], "prediction": "Gesatg muta egsitpu'nug etliang.", "reference": "Gisgug ilajit muta sapo'nug maja'sit." }, { "id": "mic-sent-a52099e66cff8318c2cca067:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Be careful, becuase if it fills with pus it will take longer to heal.", "output_text": "Ango'te'n, muta waqaiewiaq me' pgije'gt'tew ge's mu nijginug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Be careful, becuase if it fills with pus it will take longer to heal.", "mic_Latn": "Ango'te'n, muta waqaiewiaq me' pgije'gt'tew ge's mu nijginug." }, "canonical_ref": "entries/w/waqaiewiaq/waqaiewiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3d416cf82d26cc68462b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waqaiewiaq/waqaiewiaq.html", "entry_url": "https://mikmaqonline.org/entries/w/waqaiewiaq/waqaiewiaq.html", "headword": "waqaiewiaq", "example_index": 0, "raw_html_path": "raw/entries/e99de5adad61c4ca505ebb201ca937d75e210601877f067e05e96d2cf0747ea5.html", "raw_html_sha256": "8d753d3656b7d27157e947d7de0108f0fe52278771f0039d5329f8ee3a94ee43", "fetched_at": "2026-07-12T02:46:36.104Z", "recordings": [ { "recording_id": "5dbcf812a1fbf350487d17bcc806641e8b5b17eb33f89327ae7445078d6257e0", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/540/540e36fb13fc4d5870fb39bd7adebd5a4620acf21be074478da66b400dc218a8.mp3", "archive_relative_path": "raw/audio/540/540e36fb13fc4d5870fb39bd7adebd5a4620acf21be074478da66b400dc218a8.mp3" } ] } ], "prediction": "Ango'te'l, muta we'gwi'g ta'n tujiw gmu'j.", "reference": "Ango'te'n, muta waqaiewiaq me' pgije'gt'tew ge's mu nijginug." }, { "id": "mic-sent-a56dca502ddc57b965bbfc07:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That woman you're talking with is very attractive.", "output_text": "Wigwasapewit na e'pit etlagnutmaioq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That woman you're talking with is very attractive.", "mic_Latn": "Wigwasapewit na e'pit etlagnutmaioq." }, "canonical_ref": "entries/w/wigwasapewit/wigwasapewit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3b421bcc3f3405e02405", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wigwasapewit/wigwasapewit.html", "entry_url": "https://mikmaqonline.org/entries/w/wigwasapewit/wigwasapewit.html", "headword": "wigwasapewit", "example_index": 0, "raw_html_path": "raw/entries/7c89bf4ad42e3e00ce49f1514d1542507d6117e73a7e00afb9c51122ca24bc19.html", "raw_html_sha256": "53482758fe01c24df410760c56b4d9e6e1fcd744ef7b1df0f36676c6d26762ee", "fetched_at": "2026-07-12T02:47:32.016Z", "recordings": [ { "recording_id": "49b727d0a5272dfe9396252d5a980654e237ac5acf604611e65661a57db3cf9a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d17/d176435c03ec8a47c55b9d3e09072b22b278aa23e0415402b4e9b1cc6e5f43f0.mp3", "archive_relative_path": "raw/audio/d17/d176435c03ec8a47c55b9d3e09072b22b278aa23e0415402b4e9b1cc6e5f43f0.mp3" } ] } ], "prediction": "Me' we'gwi'g na wi'gatign.", "reference": "Wigwasapewit na e'pit etlagnutmaioq." }, { "id": "mic-sent-a5a43c366470e050cbb04934:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "John told me that he will be hunting tonight.", "output_text": "Sa'n telimip welo'gwetew ulo'nug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "John told me that he will be hunting tonight.", "mic_Latn": "Sa'n telimip welo'gwetew ulo'nug." }, "canonical_ref": "entries/w/welo'gwet/welo'gwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-fa9c618b411188174328", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/welo'gwet/welo'gwet.html", "entry_url": "https://mikmaqonline.org/entries/w/welo'gwet/welo'gwet.html", "headword": "welo'gwet", "example_index": 0, "raw_html_path": "raw/entries/8584ed7bec383a5fe54db07bf0a0c28d8ab78469e6326e9b34d5d3053b545657.html", "raw_html_sha256": "8c4685522ae0932cc9b89c6122182b796e58ea1e02f1ee3812ba5e8880be92a2", "fetched_at": "2026-07-12T02:36:26.960Z", "recordings": [ { "recording_id": "7af71cd45a1f95bb50ebf692defe3ec2be96c5e8c0772064f00689306f6a7056", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4c0/4c07373b2276a48f2ab7e0f07badf92ab2c2bf6260489a53e2dd534750f09c47.mp3", "archive_relative_path": "raw/audio/4c0/4c07373b2276a48f2ab7e0f07badf92ab2c2bf6260489a53e2dd534750f09c47.mp3" } ] } ], "prediction": "Sa'n telte'latl te'sipu'g ula ji'nm.", "reference": "Sa'n telimip welo'gwetew ulo'nug." }, { "id": "mic-sent-a601d8e98c10b102ccc5d997:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little boy just smashed his lip.", "output_text": "Lpa'tu'ji'j ugsi gispastestoq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little boy just smashed his lip.", "mic_Latn": "Lpa'tu'ji'j ugsi gispastestoq." }, "canonical_ref": "entries/u/ugsi/ugsi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8629ebd0f627a7dd3e2f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugsi/ugsi.html", "entry_url": "https://mikmaqonline.org/entries/u/ugsi/ugsi.html", "headword": "ugsi", "example_index": 0, "raw_html_path": "raw/entries/9437bca814dbb4a3415690b9b0c43cfab7937a435db27cf75abcfaf4e7d8e610.html", "raw_html_sha256": "2563efc5cc9642b876963b70e579ff49b4f8f3f6493c578b7dcda8bffdec9199", "fetched_at": "2026-07-12T02:46:14.931Z", "recordings": [ { "recording_id": "3ce0e32b6d60cd40783f976206f2359a63753f3a284356882b1d6a5933d9ac55", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dbc/dbc47ce7757d4ee4e1203f332cf090bc713025caacc47ed47d5689fadcaa8b0a.mp3", "archive_relative_path": "raw/audio/dbc/dbc47ce7757d4ee4e1203f332cf090bc713025caacc47ed47d5689fadcaa8b0a.mp3" } ] } ], "prediction": "Lpa'tuji'j pas'g gesatg ugjit.", "reference": "Lpa'tu'ji'j ugsi gispastestoq." }, { "id": "mic-sent-a6144e4750cf521a1c0f5550:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That a short cut on this footpath.", "output_text": "Ula pmisgma'si uggwatawti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That a short cut on this footpath.", "mic_Latn": "Ula pmisgma'si uggwatawti." }, "canonical_ref": "entries/u/uggwatawti/uggwatawti.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-42cd64e252d2f654836f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/uggwatawti/uggwatawti.html", "entry_url": "https://mikmaqonline.org/entries/u/uggwatawti/uggwatawti.html", "headword": "uggwatawti", "example_index": 0, "raw_html_path": "raw/entries/547b896b7b9f57468946c2a0c1eeb493a24d5e42bb256acb6268f6d7637b3d28.html", "raw_html_sha256": "008be4633f4782d574fefc3b10bb2ada856f110cc28e389107523535508c5d87", "fetched_at": "2026-07-12T02:46:10.107Z", "recordings": [ { "recording_id": "fbff746604e1251b43ee7ff488abeb8acead0660ff46d2c07b425b0098115871", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/613/613c86fa5eddde61d512f08c6c00ca73423ebd5f79ec798e1b5350ab47fac982.mp3", "archive_relative_path": "raw/audio/613/613c86fa5eddde61d512f08c6c00ca73423ebd5f79ec798e1b5350ab47fac982.mp3" } ] } ], "prediction": "We'gwi'g na ula pilei.", "reference": "Ula pmisgma'si uggwatawti." }, { "id": "mic-sent-a65175f6a0d0b4d3be68af2a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Each time he/she touches it he/she burns.", "output_text": "Te's sama'toq na gaqsit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Each time he/she touches it he/she burns.", "mic_Latn": "Te's sama'toq na gaqsit." }, "canonical_ref": "entries/s/sama'toq/sama'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-65d562d3048358c7fdde", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sama'toq/sama'toq.html", "entry_url": "https://mikmaqonline.org/entries/s/sama'toq/sama'toq.html", "headword": "sama'toq", "example_index": 0, "raw_html_path": "raw/entries/2b7095c446229d3f445cb46805f62769eabe2f6f6913aa6d136053891aba2a94.html", "raw_html_sha256": "c55bccccb5fcac65189d3cfae366099854c5e328a0630b2f0f5bb423bd713b25", "fetched_at": "2026-07-12T02:44:35.211Z", "recordings": [ { "recording_id": "f9b0c70cf1afc13324062db568cff713e439836e72801c977a3e9549e1d9ccf3", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ad4/ad4798a002d4aa3177372736536bce526121b272ce01c4d45675895d60d37d10.mp3", "archive_relative_path": "raw/audio/ad4/ad4798a002d4aa3177372736536bce526121b272ce01c4d45675895d60d37d10.mp3" } ] } ], "prediction": "Te's ta'n tujiw gesatg ugjit.", "reference": "Te's sama'toq na gaqsit." }, { "id": "mic-sent-a6d1a5ff06699750b0e8f90f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The old man calls him/her by many names, sometimes good, sometimes not.", "output_text": "Gisigu milui'tatl, jijuaqa gelu'lg, jijuaqa moqwa'.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The old man calls him/her by many names, sometimes good, sometimes not.", "mic_Latn": "Gisigu milui'tatl, jijuaqa gelu'lg, jijuaqa moqwa'." }, "canonical_ref": "entries/m/milui'tatl/milui'tatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6ae8a3da349591a38339", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/milui'tatl/milui'tatl.html", "entry_url": "https://mikmaqonline.org/entries/m/milui'tatl/milui'tatl.html", "headword": "milui'tatl", "example_index": 0, "raw_html_path": "raw/entries/9304cb3fe42778556d0885b0fe1c5df7aeba107974ff69525be03788fdbe2b27.html", "raw_html_sha256": "ced48a8d6d033cd1bc93e52381108945ffd7759af883febc53f598faddc20a54", "fetched_at": "2026-07-12T02:41:38.278Z", "recordings": [ { "recording_id": "743fe2517fb621ce3b480a9510bafc0ad6bd996efd62c672b13e9e39f3e6865a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/878/87824a24fd8ab5129b9474ff9a8328df9660604f5e08a18ee0d85696d71faead.mp3", "archive_relative_path": "raw/audio/878/87824a24fd8ab5129b9474ff9a8328df9660604f5e08a18ee0d85696d71faead.mp3" } ] } ], "prediction": "Gisigu'l etlmisga'latl, lpa we'gwi'j, mu lpa mu mu mu' mu'n.", "reference": "Gisigu milui'tatl, jijuaqa gelu'lg, jijuaqa moqwa'." }, { "id": "mic-sent-a6e6cf3beae8c544d628e3de:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who has cut that tree down?", "output_text": "Wen gisigewsatl na miti'sl?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who has cut that tree down?", "mic_Latn": "Wen gisigewsatl na miti'sl?" }, "canonical_ref": "entries/g/gewsatl/gewsatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ee2c3cd677cea6a52981", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gewsatl/gewsatl.html", "entry_url": "https://mikmaqonline.org/entries/g/gewsatl/gewsatl.html", "headword": "gewsatl", "example_index": 0, "raw_html_path": "raw/entries/eca44f8d12667fe629e1e591d01b6566111a247569197f9f100e6e8468628ff1.html", "raw_html_sha256": "de55cd5396d17bef7c6c385d78486667ca85df83630cea4e6bcc77a7802beec4", "fetched_at": "2026-07-12T02:39:26.812Z", "recordings": [ { "recording_id": "dd4bf02263b01282416052339047436b03356132dbd5aa01d3db759476fb0486", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9d8/9d878e3f91d4e268d78b9f20a74d47b12f7ac2ddb64d47b77b2377d5801efb48.mp3", "archive_relative_path": "raw/audio/9d8/9d878e3f91d4e268d78b9f20a74d47b12f7ac2ddb64d47b77b2377d5801efb48.mp3" } ] } ], "prediction": "Wen gisga'toq na miti'g?", "reference": "Wen gisigewsatl na miti'sl?" }, { "id": "mic-sent-a6ed21e1ba2b134169cb3da2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has a totem, the salmon.", "output_text": "Ugtuttemit, plamu'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has a totem, the salmon.", "mic_Latn": "Ugtuttemit, plamu'l." }, "canonical_ref": "entries/u/ugtuttemit/ugtuttemit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-569183f463ad67affb4a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugtuttemit/ugtuttemit.html", "entry_url": "https://mikmaqonline.org/entries/u/ugtuttemit/ugtuttemit.html", "headword": "ugtuttemit", "example_index": 0, "raw_html_path": "raw/entries/c8bf45c5505027ef9510b8d50e758da991548433d025c1d206bcc5d41963d5e9.html", "raw_html_sha256": "3753c52137bca4aaec5e3c1c91945ec09167a710c381a85badf66cc9ef7efa9f", "fetched_at": "2026-07-12T02:46:20.351Z", "recordings": [ { "recording_id": "1378e7b66988279cc10818bd55c57fa05b754a0b36f5d39a8df6dd49cd9d214f", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c6e/c6e2d71df58d147808bfdd730a4280639785c9b13ece28908f49d5fc801d045e.mp3", "archive_relative_path": "raw/audio/c6e/c6e2d71df58d147808bfdd730a4280639785c9b13ece28908f49d5fc801d045e.mp3" } ] } ], "prediction": "To'te'm, plamu'g.", "reference": "Ugtuttemit, plamu'l." }, { "id": "mic-sent-a7127b337e0756f29e18e822:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Are your grandfather and grandmother still alive?", "output_text": "Me' gmijgamij aq gugumij mimajijig?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Are your grandfather and grandmother still alive?", "mic_Latn": "Me' gmijgamij aq gugumij mimajijig?" }, "canonical_ref": "entries/m/mimajit/mimajit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d8c83b497e4368f69e3b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mimajit/mimajit.html", "entry_url": "https://mikmaqonline.org/entries/m/mimajit/mimajit.html", "headword": "mimajit", "example_index": 0, "raw_html_path": "raw/entries/3a528234a9e02fbdea8394c7dab0d6527421eda97474e92ffbb09f475d304431.html", "raw_html_sha256": "4362c87617f06fa420eaba4eac1b067a484e20710151acebcbb36f856aee6580", "fetched_at": "2026-07-12T02:41:38.684Z", "recordings": [ { "recording_id": "ea07f330ddc72c04cd8b22d45e80517444dc9861cd7298f44062c5d38bc3b913", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9b7/9b77b7b5be2450f20e1e40ac4ebfc350905dda41b799ada761bbd1f114d53ebc.mp3", "archive_relative_path": "raw/audio/9b7/9b77b7b5be2450f20e1e40ac4ebfc350905dda41b799ada761bbd1f114d53ebc.mp3" } ] } ], "prediction": "Gi's gi'l na nuji'j?", "reference": "Me' gmijgamij aq gugumij mimajijig?" }, { "id": "mic-sent-a7271fe6d5b3538fbd0da35d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I can't remember anyone who hunts for eels in the mud in winter.", "output_text": "Mu nugu' ni'n migwite'lmaq wen nantuan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I can't remember anyone who hunts for eels in the mud in winter.", "mic_Latn": "Mu nugu' ni'n migwite'lmaq wen nantuan." }, "canonical_ref": "entries/n/nantuat/nantuat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d1d2ade6f47198875694", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nantuat/nantuat.html", "entry_url": "https://mikmaqonline.org/entries/n/nantuat/nantuat.html", "headword": "nantuat", "example_index": 0, "raw_html_path": "raw/entries/ac746c135851b6fef0d6decee80765cca410de0997a765f28245bff82e3b6323.html", "raw_html_sha256": "10f086fd23975437b81e74a37d54c5cd2b7716f970dbeee617ddaba749972c20", "fetched_at": "2026-07-12T02:41:59.882Z", "recordings": [ { "recording_id": "3057308ea3965b8d6f951ae2a2abe3bc29f303a623210319b5cd1b428dfd9e94", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e44/e44c7633792aa832edf8dda234f67ffd6ed44c79ec161cd5d9ac16fb86cc4da6.mp3", "archive_relative_path": "raw/audio/e44/e44c7633792aa832edf8dda234f67ffd6ed44c79ec161cd5d9ac16fb86cc4da6.mp3" } ] } ], "prediction": "Mu ni'n te's'g ta'n tujiw gisijig pemijig.", "reference": "Mu nugu' ni'n migwite'lmaq wen nantuan." }, { "id": "mic-sent-a766cbf9087813da5f15c346:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I'll do the straining outside.", "output_text": "Ala gujmug tlsinqamistega's.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I'll do the straining outside.", "mic_Latn": "Ala gujmug tlsinqamistega's." }, "canonical_ref": "entries/s/sinqamisteget/sinqamisteget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-65e769479b642d76f9e0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sinqamisteget/sinqamisteget.html", "entry_url": "https://mikmaqonline.org/entries/s/sinqamisteget/sinqamisteget.html", "headword": "sinqamisteget", "example_index": 0, "raw_html_path": "raw/entries/26d0e70001b7b3ab61f798e63e59a944ff61e7baff9f6d50237efc266ba41677.html", "raw_html_sha256": "7e2c7113e96d2dda982bcf21176a0b463d005226b3883883789fe72ff54d0dc4", "fetched_at": "2026-07-12T02:45:03.962Z", "recordings": [ { "recording_id": "4c84b5893a49b6b0e181aeb6b0b8b9fadf61955a0a00fc72c46c6ea1bc2a1852", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/810/810824ff4589df8793715465254ef84c1d6cff139ec13f0d935e41d7833ed1c7.mp3", "archive_relative_path": "raw/audio/810/810824ff4589df8793715465254ef84c1d6cff139ec13f0d935e41d7833ed1c7.mp3" } ] } ], "prediction": "Amujpa ni'n goqwei.", "reference": "Ala gujmug tlsinqamistega's." }, { "id": "mic-sent-a769c74643dc05ed160bd025:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she rips the picture off that wall.", "output_text": "Menina'latl napui'gignn elsaqas'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she rips the picture off that wall.", "mic_Latn": "Menina'latl napui'gignn elsaqas'g." }, "canonical_ref": "entries/m/menina'latl/menina'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dfdee7837afd41116793", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/menina'latl/menina'latl.html", "entry_url": "https://mikmaqonline.org/entries/m/menina'latl/menina'latl.html", "headword": "menina'latl", "example_index": 0, "raw_html_path": "raw/entries/805d8c0e10d7915d51004cb039f62bbb8d1050d4ceeba42a582e5a114a0632f6.html", "raw_html_sha256": "19701194f560ac549ac4a8030137e56f93fd15bbf12da1daa2763dfa173ca8d8", "fetched_at": "2026-07-12T02:41:16.605Z", "recordings": [ { "recording_id": "243429cd06d725d3512019ef0b152f5f394d0a9def5aa4a93a8540581ac8b55c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/961/9614b4638290ad2c3380441c311d7df6a7fdbc86228f381c1f81800c8dd22bab.mp3", "archive_relative_path": "raw/audio/961/9614b4638290ad2c3380441c311d7df6a7fdbc86228f381c1f81800c8dd22bab.mp3" } ] } ], "prediction": "Pugwelga'latl na lpaqan.", "reference": "Menina'latl napui'gignn elsaqas'g." }, { "id": "mic-sent-a77eac073fb415c9f7d07bec:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who is planting here?", "output_text": "Wen iga'taqugt ula tet?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who is planting here?", "mic_Latn": "Wen iga'taqugt ula tet?" }, "canonical_ref": "entries/i/iga'taqug/iga'taqug.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3509f5eb9eea5ab8f661", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/iga'taqug/iga'taqug.html", "entry_url": "https://mikmaqonline.org/entries/i/iga'taqug/iga'taqug.html", "headword": "iga'taqug", "example_index": 0, "raw_html_path": "raw/entries/ddd0757235ec23d04ec5b9c8db26efbb60033d72fbf2c2ca0f3fab02bb45df39.html", "raw_html_sha256": "e61367c804d638cfb97ef4084d490d4bc20d43e9b1a52c5a6228352126cf0cc3", "fetched_at": "2026-07-12T02:40:04.710Z", "recordings": [ { "recording_id": "999c750f52d0f77a50e0f04d80ebddd76408d6808c91a6a0b735e181edca2bad", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/02d/02dd529525e794437a466a4e5db1109b32eb6e7cca9845d5cda6eadd938d9267.mp3", "archive_relative_path": "raw/audio/02d/02dd529525e794437a466a4e5db1109b32eb6e7cca9845d5cda6eadd938d9267.mp3" } ] } ], "prediction": "Wen gesatg ula tet?", "reference": "Wen iga'taqugt ula tet?" }, { "id": "mic-sent-a7c2e49f9d235c994c477e5e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is coming into view out of the fog.", "output_text": "Wejgwimusga'sit u'nigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is coming into view out of the fog.", "mic_Latn": "Wejgwimusga'sit u'nigtug." }, "canonical_ref": "entries/w/wejgwimusga'sit/wejgwimusga'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-73b92d3d361f06c40bb1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejgwimusga'sit/wejgwimusga'sit.html", "entry_url": "https://mikmaqonline.org/entries/w/wejgwimusga'sit/wejgwimusga'sit.html", "headword": "wejgwimusga'sit", "example_index": 0, "raw_html_path": "raw/entries/0fac90a0f3f5750d1e53966776c3a6acdd53a1b66c5e8bb52e2284ce89f0b6f5.html", "raw_html_sha256": "f13c80ca0ccca2be6d602b705895631813e2ac98ea1812913c4fd50361c5037d", "fetched_at": "2026-07-12T02:36:17.385Z", "recordings": [ { "recording_id": "d25be33a49795c8a27390b2ab80acbdeaec0418e4b589362d6559a54943200d7", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6ef/6efb9601df668c0af3c40e0ba95609a34fd90a0abf61a2441bcae2b85ed902aa.mp3", "archive_relative_path": "raw/audio/6ef/6efb9601df668c0af3c40e0ba95609a34fd90a0abf61a2441bcae2b85ed902aa.mp3" } ] } ], "prediction": "Pugwelg'g etlmisga'toq.", "reference": "Wejgwimusga'sit u'nigtug." }, { "id": "mic-sent-a7d4835fac19e99bb5626de2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she encourages his/her friend to go study.", "output_text": "Witapal nimji'muatl najigina'masinnin.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she encourages his/her friend to go study.", "mic_Latn": "Witapal nimji'muatl najigina'masinnin." }, "canonical_ref": "entries/n/nimji'muatl/nimji'muatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-da65c968dd11c10195d4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nimji'muatl/nimji'muatl.html", "entry_url": "https://mikmaqonline.org/entries/n/nimji'muatl/nimji'muatl.html", "headword": "nimji'muatl", "example_index": 0, "raw_html_path": "raw/entries/972818a399fbb7b697db8420de59be70c6010cb093c64dabdbdd25ce870c613e.html", "raw_html_sha256": "d6bc1692c96dfb2f0898dda45296776aba107b034955eaf747d53f944435ab2d", "fetched_at": "2026-07-12T02:42:33.921Z", "recordings": [ { "recording_id": "9b5620fcf0a062bb06020f9bc225069f83f1f6875bc5da87f0c9169e40069fe8", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/08a/08a42242a09ab48dfb828fd5f9bee081c63d9304e2ef850b6c6be4a944a7b13c.mp3", "archive_relative_path": "raw/audio/08a/08a42242a09ab48dfb828fd5f9bee081c63d9304e2ef850b6c6be4a944a7b13c.mp3" } ] } ], "prediction": "Amujpa'latl witap alugowaqan.", "reference": "Witapal nimji'muatl najigina'masinnin." }, { "id": "mic-sent-a85e0c7d8fc2679e5b4628bf:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Let me remove that last piece of bark.", "output_text": "Ge' menipqwa'tuap na mussew esgwiaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Let me remove that last piece of bark.", "mic_Latn": "Ge' menipqwa'tuap na mussew esgwiaq." }, "canonical_ref": "entries/m/menipqwa'toq/menipqwa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a20ce852adc1505b3560", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/menipqwa'toq/menipqwa'toq.html", "entry_url": "https://mikmaqonline.org/entries/m/menipqwa'toq/menipqwa'toq.html", "headword": "menipqwa'toq", "example_index": 0, "raw_html_path": "raw/entries/2a7ceb52bf4d0c5bd72184a9908aa0eac3d423eeb26f901ac91d0facd4cc25e1.html", "raw_html_sha256": "f18aa07dcb5dfd97ec97ef093fe4c43578bf08dde63adedb4267de9027e7f8ef", "fetched_at": "2026-07-12T02:41:17.106Z", "recordings": [ { "recording_id": "8c4e36b4e080fa2947c8ccb4374b525ab66ffb5d214164e30d6b603cb73f5293", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4a0/4a0d9c0dbce827d47b08e54b25a7d92a3040aa4229d9c716d44bd3270df6b9c6.mp3", "archive_relative_path": "raw/audio/4a0/4a0d9c0dbce827d47b08e54b25a7d92a3040aa4229d9c716d44bd3270df6b9c6.mp3" } ] } ], "prediction": "Ge' negm na nige' pas'g na gmu'j.", "reference": "Ge' menipqwa'tuap na mussew esgwiaq." }, { "id": "mic-sent-a865b23d91655ebed75a8975:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My aunt knits everyday.", "output_text": "Nsugwis elisgnuet tesigisg'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My aunt knits everyday.", "mic_Latn": "Nsugwis elisgnuet tesigisg'g." }, "canonical_ref": "entries/e/elisgnuet/elisgnuet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d8e19408a10787f62e10", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elisgnuet/elisgnuet.html", "entry_url": "https://mikmaqonline.org/entries/e/elisgnuet/elisgnuet.html", "headword": "elisgnuet", "example_index": 0, "raw_html_path": "raw/entries/5653f5e2c93732e61361ad98ddfe2a7bdfdd13ca472280559aa3fbffad7966c2.html", "raw_html_sha256": "e4ab4774858f86e592a342c6f2c1d169a7782d4adfba8deac90ca2a0ce66c21d", "fetched_at": "2026-07-12T02:37:46.909Z", "recordings": [ { "recording_id": "2b32aed4a9b8dc8ce98b9f0c6f47064cc908fe8842f27ffbc6e794463b55c1c1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6a8/6a801c2a32084c285f3165fed62aa514b22de8366e1d2a13a2890f852515cd72.mp3", "archive_relative_path": "raw/audio/6a8/6a801c2a32084c285f3165fed62aa514b22de8366e1d2a13a2890f852515cd72.mp3" } ] } ], "prediction": "Nsugwi'g na nugu' te'sipu'g.", "reference": "Nsugwis elisgnuet tesigisg'g." }, { "id": "mic-sent-a88454e6ef05905f45c055d0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has smashed his/her thumb.", "output_text": "Ugtijin gisipaste'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has smashed his/her thumb.", "mic_Latn": "Ugtijin gisipaste'g." }, "canonical_ref": "entries/u/ugtijin/ugtijin.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4b83eac14e70ea74d670", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugtijin/ugtijin.html", "entry_url": "https://mikmaqonline.org/entries/u/ugtijin/ugtijin.html", "headword": "ugtijin", "example_index": 0, "raw_html_path": "raw/entries/1543c12251d7ff0d5d99d87636fd3c6a9069f1bc88dee518b2abf3d35786aede.html", "raw_html_sha256": "e24a73d880c6fb64faf493a6e075ce4cea890ce2f7410be0a221d20078b58152", "fetched_at": "2026-07-12T02:46:17.725Z", "recordings": [ { "recording_id": "296bfaf0dc9df31cfd686a9296a6bc7a38c1e3683a40046da78cdb047f1c081a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6af/6af5095caaa184c0090b13c5b74db65a2daa6ebc519315b9495a7e2249f1ecf8.mp3", "archive_relative_path": "raw/audio/6af/6af5095caaa184c0090b13c5b74db65a2daa6ebc519315b9495a7e2249f1ecf8.mp3" } ] } ], "prediction": "Gesatg ugta'latl ugjitl.", "reference": "Ugtijin gisipaste'g." }, { "id": "mic-sent-a88e35e52d59bf47abccaf39:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Four logs are sitting alongside the shore.", "output_text": "Ne'wijig tmoqta'wgw jajigoqpultijig sitmug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Four logs are sitting alongside the shore.", "mic_Latn": "Ne'wijig tmoqta'wgw jajigoqpultijig sitmug." }, "canonical_ref": "entries/j/jajigoqpit/jajigoqpit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dce63e048becbe68ce95", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jajigoqpit/jajigoqpit.html", "entry_url": "https://mikmaqonline.org/entries/j/jajigoqpit/jajigoqpit.html", "headword": "jajigoqpit", "example_index": 0, "raw_html_path": "raw/entries/da508915f6815c94cbe01cc8ca59e9666d08c935e0724c30fe5b624bbfad98ac.html", "raw_html_sha256": "feca9eb98b0bc036553c8b3b9f1c2279437685c4cef03d33c86b3b3bcf1fb610", "fetched_at": "2026-07-12T02:40:13.684Z", "recordings": [ { "recording_id": "e5e28dec267a78a002dc24fd35d138b9f77cf46f647bfff0b54ba9730919e3da", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/015/0156d788f5c506bd266acb76aacdc851bfb0a13028ccc3aec30611f1b4f130fb.mp3", "archive_relative_path": "raw/audio/015/0156d788f5c506bd266acb76aacdc851bfb0a13028ccc3aec30611f1b4f130fb.mp3" } ] } ], "prediction": "Na'te's'g ugta'sijig ta'n te'sipowji'jig.", "reference": "Ne'wijig tmoqta'wgw jajigoqpultijig sitmug." }, { "id": "mic-sent-a8a1333c19eefc3ef78a4f19:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I believe they will arrive tomorrow.", "output_text": "Telte'lmgig sapo'nug pe'ita'taq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I believe they will arrive tomorrow.", "mic_Latn": "Telte'lmgig sapo'nug pe'ita'taq." }, "canonical_ref": "entries/t/telte'lmatl/telte'lmatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-92db86ba5d8314083b65", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/telte'lmatl/telte'lmatl.html", "entry_url": "https://mikmaqonline.org/entries/t/telte'lmatl/telte'lmatl.html", "headword": "telte'lmatl", "example_index": 0, "raw_html_path": "raw/entries/449befe43ffd161f630762cceab990a6a892a18b68b2a5269780dad842542dcf.html", "raw_html_sha256": "7ea8c384f963f9fb7ff3710cc5fca33184b1766c353faf4e2ed4d75323130f25", "fetched_at": "2026-07-12T02:45:34.812Z", "recordings": [ { "recording_id": "202ffb22ac81b0df49f439807cf59c9bf90c078ba9b88fd61fcde230324b4432", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/af1/af16b9318c549a4191f75c7c4bffcc8ad0bf1db0c40757002ab729d0e4ad53f2.mp3", "archive_relative_path": "raw/audio/af1/af16b9318c549a4191f75c7c4bffcc8ad0bf1db0c40757002ab729d0e4ad53f2.mp3" } ] } ], "prediction": "Telo'tm e'pite's'g gisgug.", "reference": "Telte'lmgig sapo'nug pe'ita'taq." }, { "id": "mic-sent-a8af9a8b9e729e837db864a1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When he/she heard his/her female friend would visit, he/she was happy.", "output_text": "Nutmateg mitugwalgutal witape'sgwal, welta'sip.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When he/she heard his/her female friend would visit, he/she was happy.", "mic_Latn": "Nutmateg mitugwalgutal witape'sgwal, welta'sip." }, "canonical_ref": "entries/w/welta'sit/welta'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8668c987ed4e5d9744ab", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/welta'sit/welta'sit.html", "entry_url": "https://mikmaqonline.org/entries/w/welta'sit/welta'sit.html", "headword": "welta'sit", "example_index": 0, "raw_html_path": "raw/entries/07e055f06aa129debb0b38cd3b203e777da1bdb3378bdfaf51f9b13e5ff42d85.html", "raw_html_sha256": "48b7149ada4f246d9a522cd7208da1bbaf302def0ebfc9c2af04cdb640ac69b5", "fetched_at": "2026-07-12T02:47:09.224Z", "recordings": [ { "recording_id": "e47bf21fec6b1ac2e474e874dbe51626167ba7b3bfdc4507c0ede2c3ee400a26", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6eb/6eb0c6a2b8246d0e214d0a56cba360511e7643ad6faa3bee66f4b65397a1b742.mp3", "archive_relative_path": "raw/audio/6eb/6eb0c6a2b8246d0e214d0a56cba360511e7643ad6faa3bee66f4b65397a1b742.mp3" } ] } ], "prediction": "Ta'n tujiw tlia'latl witapal, wesamgwet.", "reference": "Nutmateg mitugwalgutal witape'sgwal, welta'sip." }, { "id": "mic-sent-a91389b4ed4000406195ae0f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The weather is awful when it rains as much as it is raining.", "output_text": "Metuigisg'g ta'n tujiw telmamungigpesaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The weather is awful when it rains as much as it is raining.", "mic_Latn": "Metuigisg'g ta'n tujiw telmamungigpesaq." }, "canonical_ref": "entries/m/metuigisg'g/metuigisg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1547d6e410f257f7126a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/metuigisg'g/metuigisg'g.html", "entry_url": "https://mikmaqonline.org/entries/m/metuigisg'g/metuigisg'g.html", "headword": "metuigisg'g", "example_index": 0, "raw_html_path": "raw/entries/6b80aaae4815911ec1ad96018ba25ec5dec89dd6f371843ed59c10892f1b5e1c.html", "raw_html_sha256": "58591fedfe0b37006098ea670fca050521c905ec10c4a643010038562c8ff7fa", "fetched_at": "2026-07-12T02:41:29.307Z", "recordings": [ { "recording_id": "498ecfc5b6e66c14f7ac431fe2527996f4a48b42576b8c7d2ab522e47905359f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/980/98063a44c71fbb4122bfd789c16561fe99e3212f5fb1fbe56191a0398d9099ca.mp3", "archive_relative_path": "raw/audio/980/98063a44c71fbb4122bfd789c16561fe99e3212f5fb1fbe56191a0398d9099ca.mp3" } ] } ], "prediction": "We'gwi'g na ta'n tujiw pas'g te's goqwei.", "reference": "Metuigisg'g ta'n tujiw telmamungigpesaq." }, { "id": "mic-sent-a931125f09afb876568fb3a2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A grilse is a young salmon.", "output_text": "Taqawan na maljewe'j plamu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A grilse is a young salmon.", "mic_Latn": "Taqawan na maljewe'j plamu." }, "canonical_ref": "entries/t/taqawan/taqawan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b1706852fbf78429f0f9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/taqawan/taqawan.html", "entry_url": "https://mikmaqonline.org/entries/t/taqawan/taqawan.html", "headword": "taqawan", "example_index": 0, "raw_html_path": "raw/entries/e07f0e3d0765e9f26a0a55035d81485d5991cb88887a52a9b332e6b11c627f31.html", "raw_html_sha256": "53bec3a2f157db9cf503ec1f0ab24fad924b39cc7b3d0b92e58d85d630b93b75", "fetched_at": "2026-07-12T02:45:25.260Z", "recordings": [ { "recording_id": "2287135d69013a9e4112e82bb522326614de7fe707bf07a1bcedd987d2a1c19f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9f7/9f7db99e3dd7a836e0012333782b5e3b9182a85584808434ed69e6acfe9722cc.mp3", "archive_relative_path": "raw/audio/9f7/9f7db99e3dd7a836e0012333782b5e3b9182a85584808434ed69e6acfe9722cc.mp3" } ] } ], "prediction": "Pugwelg na plamu'ji'j.", "reference": "Taqawan na maljewe'j plamu." }, { "id": "mic-sent-a94551a2db8ebe6e14c7f404:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Whenever I help out my friend he only takes advantage and doesn't work.", "output_text": "Te's apoqnmaq nitap na awna massaqa'sitew aq ma' lugwegw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Whenever I help out my friend he only takes advantage and doesn't work.", "mic_Latn": "Te's apoqnmaq nitap na awna massaqa'sitew aq ma' lugwegw." }, "canonical_ref": "entries/m/massaqa'sit/massaqa'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-beb434daa23fdf1fc03f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/massaqa'sit/massaqa'sit.html", "entry_url": "https://mikmaqonline.org/entries/m/massaqa'sit/massaqa'sit.html", "headword": "massaqa'sit", "example_index": 0, "raw_html_path": "raw/entries/f5536a7a487a0de272d5fbf4930182495a74a8b868904d8f660a8997b6a870e7.html", "raw_html_sha256": "4d56bd533b60f85af6178646a30a67b02290f32fac2080fac4127be50166278f", "fetched_at": "2026-07-12T02:40:53.873Z", "recordings": [ { "recording_id": "23f43c7832c9b4d50523a1efe2d53904c1eec6b5cbc07c57dc6e2410a48ea5da", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ec4/ec44acaef57da085818522fcc29a1890032cfa051e1b031a0222ae014b36cd2d.mp3", "archive_relative_path": "raw/audio/ec4/ec44acaef57da085818522fcc29a1890032cfa051e1b031a0222ae014b36cd2d.mp3" } ] } ], "prediction": "Ta'n tujiw nitap lpa nitap pas'g etlmisga'toq aq mu negm.", "reference": "Te's apoqnmaq nitap na awna massaqa'sitew aq ma' lugwegw." }, { "id": "mic-sent-a9eb607ef64e027fe8160fa7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My dog knows how to make himself the center of attention.", "output_text": "Ntue'm mawinta'ne'tma'sit, gesatg me'ga'sualuj.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My dog knows how to make himself the center of attention.", "mic_Latn": "Ntue'm mawinta'ne'tma'sit, gesatg me'ga'sualuj." }, "canonical_ref": "entries/n/ne'tma'sit/ne'tma'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f7ff5caaf55df543e2d5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ne'tma'sit/ne'tma'sit.html", "entry_url": "https://mikmaqonline.org/entries/n/ne'tma'sit/ne'tma'sit.html", "headword": "ne'tma'sit", "example_index": 0, "raw_html_path": "raw/entries/8e26b652d3634dee873948f338df065f93be41c7d782c922b162977f9f09c39b.html", "raw_html_sha256": "275e810a18ace625bcf77e3f70b9d64b981ff4800b36d61150c5f4c0de3723ab", "fetched_at": "2026-07-12T02:42:25.474Z", "recordings": [ { "recording_id": "2835a04fab218d0d1b54cb436c4724b847d923cdcbe2b035759ab4838281203b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ed2/ed251e589a6572da48f70308cee4b96d61deece231091478b175bfb529c71a42.mp3", "archive_relative_path": "raw/audio/ed2/ed251e589a6572da48f70308cee4b96d61deece231091478b175bfb529c71a42.mp3" } ] } ], "prediction": "Nmu'ji'j gesatg ta'n tujiw we'gwigtug.", "reference": "Ntue'm mawinta'ne'tma'sit, gesatg me'ga'sualuj." }, { "id": "mic-sent-aae02e9dfcf24cf4a4007865:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Use little rags to clean your vehicle.", "output_text": "Misegnu'jl e'wen waqama'tu'n gutepaqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Use little rags to clean your vehicle.", "mic_Latn": "Misegnu'jl e'wen waqama'tu'n gutepaqan." }, "canonical_ref": "entries/m/misegnu'j/misegnu'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-26a9917c58e86baa18b2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/misegnu'j/misegnu'j.html", "entry_url": "https://mikmaqonline.org/entries/m/misegnu'j/misegnu'j.html", "headword": "misegnu'j", "example_index": 0, "raw_html_path": "raw/entries/fb6fe393bdfca9b65ce29ae6254a24bc1fa3e99eda75ff517efe5e3af37767f7.html", "raw_html_sha256": "cb2103e7ac4cd177cd902c39637c4db8d794de79e8dbf5f497ff161b0960aea7", "fetched_at": "2026-07-12T02:41:41.323Z", "recordings": [ { "recording_id": "54061d3873ecbfe3ea7397927142a3d6e589df197365a14dfeb12d32e2c53052", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ca0/ca0f5f6d9254ff22118e1aab02166eb40b22ccd3f013258fd6651026207af6d2.mp3", "archive_relative_path": "raw/audio/ca0/ca0f5f6d9254ff22118e1aab02166eb40b22ccd3f013258fd6651026207af6d2.mp3" } ] } ], "prediction": "Amujpa'tu'ji'j gmu'j utepaqan ugjit.", "reference": "Misegnu'jl e'wen waqama'tu'n gutepaqan." }, { "id": "mic-sent-aaff9a6ea970bb42c5729a31:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Here he/she comes with the ball again.", "output_text": "Gi's ap ula wejgwa'latl tu'waqann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Here he/she comes with the ball again.", "mic_Latn": "Gi's ap ula wejgwa'latl tu'waqann." }, "canonical_ref": "entries/w/wejgwa'latl/wejgwa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-fb92143ef27da4a1b6be", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejgwa'latl/wejgwa'latl.html", "entry_url": "https://mikmaqonline.org/entries/w/wejgwa'latl/wejgwa'latl.html", "headword": "wejgwa'latl", "example_index": 0, "raw_html_path": "raw/entries/a6fa0165682c0aca583fd986fa74506ecb4c6218e2f8594ebe1b484144d1f264.html", "raw_html_sha256": "01df99579fef7c92a73ed52e8d9dd1970e241fb749eee80f38c4db36ca9720bf", "fetched_at": "2026-07-12T02:46:50.083Z", "recordings": [ { "recording_id": "87b64f155fd74a606f42b357371d0cbedc3727d5613e29c1427faf016890920d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ebc/ebc165deccabc014e954c952d0bf3c0f908585df04cf4bb339bbda3858830e2c.mp3", "archive_relative_path": "raw/audio/ebc/ebc165deccabc014e954c952d0bf3c0f908585df04cf4bb339bbda3858830e2c.mp3" } ] } ], "prediction": "Ula gi's newtepa'latl ugta'qann.", "reference": "Gi's ap ula wejgwa'latl tu'waqann." }, { "id": "mic-sent-abcb076c3c9274318bf47636:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My grandchild and I went to the edge of the woods and immediately came back.", "output_text": "Nuji'j weja'tieg gegiasqatug aq smtug apa'ja'tieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My grandchild and I went to the edge of the woods and immediately came back.", "mic_Latn": "Nuji'j weja'tieg gegiasqatug aq smtug apa'ja'tieg." }, "canonical_ref": "entries/g/gegiasqatug/gegiasqatug.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-97fe97639e52f1d0fd90", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gegiasqatug/gegiasqatug.html", "entry_url": "https://mikmaqonline.org/entries/g/gegiasqatug/gegiasqatug.html", "headword": "gegiasqatug", "example_index": 0, "raw_html_path": "raw/entries/3603f0f9cd54aac0676e3b0c91360eab6788d901a1e5c77c1948f4b884cb57fd.html", "raw_html_sha256": "75badf182db3e0cb677361bb1eebe893f455622dea244205729a4a966a389f35", "fetched_at": "2026-07-12T02:36:28.770Z", "recordings": [ { "recording_id": "6dd87d72ce2e0072df5b5e9bd9dbf25d09f12fa9c04bcaad978acfdbf0c2d92e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/962/962d01d49f3013d0e516389f687c92c1ee8747d2a9a71118aeb49ae0f9283deb.mp3", "archive_relative_path": "raw/audio/962/962d01d49f3013d0e516389f687c92c1ee8747d2a9a71118aeb49ae0f9283deb.mp3" } ] } ], "prediction": "Nuji'j aq ni'n gi's'tmu'jig aq tujiw mesgi'g.", "reference": "Nuji'j weja'tieg gegiasqatug aq smtug apa'ja'tieg." }, { "id": "mic-sent-ac1f1c6df2317423a232e992:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I went picking fiddleheads and now my pails are full to the brim with them.", "output_text": "Aptapia'ji'jgewatpe'gei aq ntla'taqsunmg nige' tmaqanigju'ejig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I went picking fiddleheads and now my pails are full to the brim with them.", "mic_Latn": "Aptapia'ji'jgewatpe'gei aq ntla'taqsunmg nige' tmaqanigju'ejig." }, "canonical_ref": "entries/t/tmaqanigju'et/tmaqanigju'et.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-435e7d048a2c5c3a3fc4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tmaqanigju'et/tmaqanigju'et.html", "entry_url": "https://mikmaqonline.org/entries/t/tmaqanigju'et/tmaqanigju'et.html", "headword": "tmaqanigju'et", "example_index": 0, "raw_html_path": "raw/entries/270f0b5ad4a1454f0b6732c43e3a69b27f1e63e375021196b4ffb9b0fc41d8a3.html", "raw_html_sha256": "3fb1474d98e3a146a51f7f53e7ab841b349ca630ea9de21a93c1066601fd0ea1", "fetched_at": "2026-07-12T02:45:59.853Z", "recordings": [ { "recording_id": "fdc84ee08d838b1dbbc17c661d9a44b372f973422c6fa01f8bf7c0da5c13c265", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c57/c571c2479e48368674069eda68b55bbbf986496139baf381a3dd5e5fe84b8765.mp3", "archive_relative_path": "raw/audio/c57/c571c2479e48368674069eda68b55bbbf986496139baf381a3dd5e5fe84b8765.mp3" } ] } ], "prediction": "Ge's na'te'l aq nige' nugu' mesgi'g nmu'ji'j.", "reference": "Aptapia'ji'jgewatpe'gei aq ntla'taqsunmg nige' tmaqanigju'ejig." }, { "id": "mic-sent-ac47ed6bbf99fedb9a9ba318:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Every morning my pets disturbes my sleep because they want me to get up and feed them.", "output_text": "Te'siegsitpu'g ntue'mg wespaiwijig muta pualijig mnja'sin aq smman.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Every morning my pets disturbes my sleep because they want me to get up and feed them.", "mic_Latn": "Te'siegsitpu'g ntue'mg wespaiwijig muta pualijig mnja'sin aq smman." }, "canonical_ref": "entries/w/wespaiwatl/wespaiwatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d7e3d872ce06af645b07", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wespaiwatl/wespaiwatl.html", "entry_url": "https://mikmaqonline.org/entries/w/wespaiwatl/wespaiwatl.html", "headword": "wespaiwatl", "example_index": 0, "raw_html_path": "raw/entries/6292261b55eea8f5d85b8a22b20e05d8b6fc6bd8844972bf3c75be956c067e7b.html", "raw_html_sha256": "7f624af920898271ffa8d141b75b8eaffd667ebd7a2489d97c64eb272762b75d", "fetched_at": "2026-07-12T02:47:20.254Z", "recordings": [ { "recording_id": "036bd59a84fbd8e2a0fab1e2d3293b03cbac6084267943c2ae1956a2187ee099", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e2a/e2a12889574f47f313bb0bfefa1f203f996e3e0d9281adc3608309bddc0c823f.mp3", "archive_relative_path": "raw/audio/e2a/e2a12889574f47f313bb0bfefa1f203f996e3e0d9281adc3608309bddc0c823f.mp3" } ] } ], "prediction": "Te'siegsitpu'g ngwis nmu'j gesatmu'tmu'n muta getu' etlma'tu'n.", "reference": "Te'siegsitpu'g ntue'mg wespaiwijig muta pualijig mnja'sin aq smman." }, { "id": "mic-sent-acd9edc3e35c6e3925712e79:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The children make a hole.", "output_text": "Mijua'ji'jg eltu'tij elmalqei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The children make a hole.", "mic_Latn": "Mijua'ji'jg eltu'tij elmalqei." }, "canonical_ref": "entries/e/elmalqei/elmalqei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8616ae85fd00be2ce88e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elmalqei/elmalqei.html", "entry_url": "https://mikmaqonline.org/entries/e/elmalqei/elmalqei.html", "headword": "elmalqei", "example_index": 0, "raw_html_path": "raw/entries/232512562c111ddccade9bcd24f2a51b228c7d26a82a0a19cf73eeba57fa9606.html", "raw_html_sha256": "97175faca9d493016dfdb5237df5a91f7438c55400ebbb1f7081076fd967a151", "fetched_at": "2026-07-12T02:37:48.223Z", "recordings": [ { "recording_id": "3dd26fdc16daad60d240c0d7a51784e70393dcb04f409b9b5a26d766beca56ba", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/20c/20c892a4fd4cfb27ee84baf697211bdd7b375de015d49ee09c17de1104fe5e25.mp3", "archive_relative_path": "raw/audio/20c/20c892a4fd4cfb27ee84baf697211bdd7b375de015d49ee09c17de1104fe5e25.mp3" } ] } ], "prediction": "Lpa'tuji'j etlmisga'toq.", "reference": "Mijua'ji'jg eltu'tij elmalqei." }, { "id": "mic-sent-ad618f5a25ab7245965f9e65:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He's been a soldier so long, he's become flatfooted.", "output_text": "Tetujisa'q sma'gnisuit, lpa nugu' peqanqasita'teget.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He's been a soldier so long, he's become flatfooted.", "mic_Latn": "Tetujisa'q sma'gnisuit, lpa nugu' peqanqasita'teget." }, "canonical_ref": "entries/p/peqanqasita'teget/peqanqasita'teget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4cd94b159dbe469f57cc", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/peqanqasita'teget/peqanqasita'teget.html", "entry_url": "https://mikmaqonline.org/entries/p/peqanqasita'teget/peqanqasita'teget.html", "headword": "peqanqasita'teget", "example_index": 0, "raw_html_path": "raw/entries/255877bbc2410f83c600fc7a267d07243e581795c9878969f9d3bab460e5305d.html", "raw_html_sha256": "408964589df7230d44e62b053a055b74827b0bdbb291aaacd9e59c3715f04d8f", "fetched_at": "2026-07-12T02:43:40.350Z", "recordings": [ { "recording_id": "8ea8a0f76f79f8971987423667511c41d65ddd4a49144665513ad438f6042e86", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/79c/79c2f04003f15e2fcf5d949b5e3014e0e88a6aa00a8d156c7ab2efedbe4f8f7f.mp3", "archive_relative_path": "raw/audio/79c/79c2f04003f15e2fcf5d949b5e3014e0e88a6aa00a8d156c7ab2efedbe4f8f7f.mp3" } ] } ], "prediction": "Te's te'sipowji'jig, lpa pugsugwet.", "reference": "Tetujisa'q sma'gnisuit, lpa nugu' peqanqasita'teget." }, { "id": "mic-sent-add1ae8e296b9b0ae6e87f4e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I find this one looks different, I don't think it is the same.", "output_text": "Piltuaptm ula, etug mu wijei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I find this one looks different, I don't think it is the same.", "mic_Latn": "Piltuaptm ula, etug mu wijei." }, "canonical_ref": "entries/p/piltuapt'g/piltuapt'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-797f3b032b0e59d46b83", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/piltuapt'g/piltuapt'g.html", "entry_url": "https://mikmaqonline.org/entries/p/piltuapt'g/piltuapt'g.html", "headword": "piltuapt'g", "example_index": 0, "raw_html_path": "raw/entries/5d0c18468ba598b2c7473d37a30726397f54dcdc6863fd1c160ffc41b4ef5a98.html", "raw_html_sha256": "080f7ee43a157d8ab78be121a2bdac9594106b2c5429edf1fce71adce7df8b4c", "fetched_at": "2026-07-12T02:43:58.130Z", "recordings": [ { "recording_id": "59f2e798368ed15ff454d6875aa4e8c8df49f731aa3929b910a9aa9de62be046", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/034/034fe0a081904aded89eac445c72870899dbe43f1c30861d9c042588e9e47af0.mp3", "archive_relative_path": "raw/audio/034/034fe0a081904aded89eac445c72870899dbe43f1c30861d9c042588e9e47af0.mp3" } ] } ], "prediction": "Newte'l na ula, mu telte'w ta'n te's'g.", "reference": "Piltuaptm ula, etug mu wijei." }, { "id": "mic-sent-ae1126625cb3cff046ccdbd2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My son falls backwarks on the floor.", "output_text": "Ngwis atuasgweitesing msaqtaqtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My son falls backwarks on the floor.", "mic_Latn": "Ngwis atuasgweitesing msaqtaqtug." }, "canonical_ref": "entries/a/atuasgweitesing/atuasgweitesing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d52191f4aafc3c8e5121", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/atuasgweitesing/atuasgweitesing.html", "entry_url": "https://mikmaqonline.org/entries/a/atuasgweitesing/atuasgweitesing.html", "headword": "atuasgweitesing", "example_index": 0, "raw_html_path": "raw/entries/c633704c4d02d78f1161ddf2ac04e77b80688421d6c12951f89c30c25b1c86d6.html", "raw_html_sha256": "cfb43dce243a3a4dc4d37acd600f83411a1ce3d10ebd2e8301b56ffa67f2724d", "fetched_at": "2026-07-12T02:37:27.062Z", "recordings": [ { "recording_id": "5b9d488f23fa52ad86f1e6c30365678a2d44c850135f7c4b984bae02b9ec0c73", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/730/730a36b414a7e66e8971d62c0f759bbc59a587b8266b5a080edc1d9462f32e1d.mp3", "archive_relative_path": "raw/audio/730/730a36b414a7e66e8971d62c0f759bbc59a587b8266b5a080edc1d9462f32e1d.mp3" } ] } ], "prediction": "Ngwis gesgm'g na wi'gatign.", "reference": "Ngwis atuasgweitesing msaqtaqtug." }, { "id": "mic-sent-ae21a58fe3aa85c726b8a795:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Lamp globe swayed first before it fell.", "output_text": "Piglewji'j tmg nanamo'qiet gesgmnaq nisiegweg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Lamp globe swayed first before it fell.", "mic_Latn": "Piglewji'j tmg nanamo'qiet gesgmnaq nisiegweg." }, "canonical_ref": "entries/n/nanamo'qiet/nanamo'qiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c5a538b32bda06b229b2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nanamo'qiet/nanamo'qiet.html", "entry_url": "https://mikmaqonline.org/entries/n/nanamo'qiet/nanamo'qiet.html", "headword": "nanamo'qiet", "example_index": 0, "raw_html_path": "raw/entries/cfeb00d0e73fb5d8202de5cfd1bd516cdcf52f22433292a55f62e5222e2079b3.html", "raw_html_sha256": "75279ca5d5c04a22aa29d8ac1b405171888f05e59b6db694bdf89f4cbf4caaab", "fetched_at": "2026-07-12T02:41:57.988Z", "recordings": [ { "recording_id": "83cc6aa4cb218556f06ea5ba0989cb0992f2924e905bd9773b3455ba27c51101", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/74f/74ffa7d4ba2b8eb4e10917f49d80038b7db443f59c5e4d04d06b29b11a64d2cf.mp3", "archive_relative_path": "raw/audio/74f/74ffa7d4ba2b8eb4e10917f49d80038b7db443f59c5e4d04d06b29b11a64d2cf.mp3" } ] } ], "prediction": "Pugwelga'toq gesgmnaq pas'g we'gwigtug.", "reference": "Piglewji'j tmg nanamo'qiet gesgmnaq nisiegweg." }, { "id": "mic-sent-aedaf3881e4684a2d28c0311:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Very early in the morning he/she goes down to the water to remove nets.", "output_text": "Gesiegsitpu'g metoqiet natqa'piet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Very early in the morning he/she goes down to the water to remove nets.", "mic_Latn": "Gesiegsitpu'g metoqiet natqa'piet." }, "canonical_ref": "entries/n/natqa'piet/natqa'piet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3e959d1ba7146ef1d12a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/natqa'piet/natqa'piet.html", "entry_url": "https://mikmaqonline.org/entries/n/natqa'piet/natqa'piet.html", "headword": "natqa'piet", "example_index": 0, "raw_html_path": "raw/entries/7adb194fe076b07624c86543221df06dad9b57dabafb3fe3d313f61d67605269.html", "raw_html_sha256": "def1ea91121942f4b6d50303c8d3d1073570c66e25f7c16a56e5b0d0fd0cd0ab", "fetched_at": "2026-07-12T02:42:13.191Z", "recordings": [ { "recording_id": "aacbbc7b246dea9b42a146dd4c2a58d83d5d1baa02a54309d58a1355e7d27958", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9cd/9cd4dd5c87a2daa98e8f0ae354e1e534b8f1689cfd3061c7123dbd4f0c87da04.mp3", "archive_relative_path": "raw/audio/9cd/9cd4dd5c87a2daa98e8f0ae354e1e534b8f1689cfd3061c7123dbd4f0c87da04.mp3" } ] } ], "prediction": "Te'siegsitpu'g esgm'g etlmisga'toq na'te's'g ta'n tujiw.", "reference": "Gesiegsitpu'g metoqiet natqa'piet." }, { "id": "mic-sent-af1fa359ce986c45205362a7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "They have finally decided to stop nagging each other.", "output_text": "Glapis gatu gisite'tmi'tij punajimtinew.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "They have finally decided to stop nagging each other.", "mic_Latn": "Glapis gatu gisite'tmi'tij punajimtinew." }, "canonical_ref": "entries/p/punajimatl/punajimatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6ec591d932969a22b9ad", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/punajimatl/punajimatl.html", "entry_url": "https://mikmaqonline.org/entries/p/punajimatl/punajimatl.html", "headword": "punajimatl", "example_index": 0, "raw_html_path": "raw/entries/0811c93454af8456d1aad6a88c4bb03aa4f0823b28196d5e43552f4cc7a4fe9a.html", "raw_html_sha256": "fdc09a51bb4bb7f0b2530ef78e5927236c2cf5dffe0ca108b306bfd9a7ab354e", "fetched_at": "2026-07-12T02:44:25.980Z", "recordings": [ { "recording_id": "5888a103ae869a1069afdf3fc7e01c95aa9ec12bda816de0ef85bfa52bd75a5c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d4d/d4daf2001eee995ad311add3c29cf6c8129f494f6fb447cf4690600a8da42ef5.mp3", "archive_relative_path": "raw/audio/d4d/d4daf2001eee995ad311add3c29cf6c8129f494f6fb447cf4690600a8da42ef5.mp3" } ] } ], "prediction": "Pugwelg'p'tm'g na'te's'g ta'n tujiw mesga'toq.", "reference": "Glapis gatu gisite'tmi'tij punajimtinew." }, { "id": "mic-sent-af69b372b7c220139acc7c3c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I've got to quickly dry my hair before I leave.", "output_text": "Amujpa jaqalipiasm nusapun gesgmnaq maja'siw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I've got to quickly dry my hair before I leave.", "mic_Latn": "Amujpa jaqalipiasm nusapun gesgmnaq maja'siw." }, "canonical_ref": "entries/j/jaqalipiasg/jaqalipiasg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dbea16c7b9e9fa9814e9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jaqalipiasg/jaqalipiasg.html", "entry_url": "https://mikmaqonline.org/entries/j/jaqalipiasg/jaqalipiasg.html", "headword": "jaqalipiasg", "example_index": 0, "raw_html_path": "raw/entries/dcfd15c0050e8b7c1d01f48ef00fd42250d97bced86e0c72cd5e7838b36ac18d.html", "raw_html_sha256": "e4a81908d862a378b421109f001cb7b018092f0beecd6935f988529c2b908a81", "fetched_at": "2026-07-12T02:40:15.002Z", "recordings": [ { "recording_id": "efc59ca8a52067021b2c8064ca6b288ec463a87870e89d241b7928eddf2925d5", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b23/b23cb25ba392e374281112b57968bd0633dd13e375050d099128241cdfc4db69.mp3", "archive_relative_path": "raw/audio/b23/b23cb25ba392e374281112b57968bd0633dd13e375050d099128241cdfc4db69.mp3" } ] } ], "prediction": "Amujpa ms't amujpa'toq ntul gesgmnaq ma' gisiw.", "reference": "Amujpa jaqalipiasm nusapun gesgmnaq maja'siw." }, { "id": "mic-sent-afcd827aeccbb79195c6390a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You don't see many wells today.", "output_text": "Mu' nugu' nemitu'nn nqano'pati'l gisgug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You don't see many wells today.", "mic_Latn": "Mu' nugu' nemitu'nn nqano'pati'l gisgug." }, "canonical_ref": "entries/n/nqano'pati/nqano'pati.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1a9dc5aff7e2abd348a2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nqano'pati/nqano'pati.html", "entry_url": "https://mikmaqonline.org/entries/n/nqano'pati/nqano'pati.html", "headword": "nqano'pati", "example_index": 0, "raw_html_path": "raw/entries/8698beeaf4114bb4c75d2bc6523f6b3d721de7a5170d4cb78c11c3e8415eae3a.html", "raw_html_sha256": "cbf8ddb4ef54dfca8bcfd2ee548d2d1f9baf3476a7b118b263ddb3ae68341810", "fetched_at": "2026-07-12T02:42:43.160Z", "recordings": [ { "recording_id": "7f7cadd30a1f7ae103ed0427931e7f5251187b3b463a80217d896106f1a05ca4", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8b7/8b74383a36f6635b14baeee998562a128e5aa2094fe623803500bf4f212436b4.mp3", "archive_relative_path": "raw/audio/8b7/8b74383a36f6635b14baeee998562a128e5aa2094fe623803500bf4f212436b4.mp3" } ] } ], "prediction": "Mu gisgug mu' nugu' gesgm'g.", "reference": "Mu' nugu' nemitu'nn nqano'pati'l gisgug." }, { "id": "mic-sent-afe80c52d5d0635b7878731d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "His/her tooth is hurting him/her.", "output_text": "Wipit gesnuwaj.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "His/her tooth is hurting him/her.", "mic_Latn": "Wipit gesnuwaj." }, "canonical_ref": "entries/w/wipit/wipit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-38a22423ec76b1a10ad6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wipit/wipit.html", "entry_url": "https://mikmaqonline.org/entries/w/wipit/wipit.html", "headword": "wipit", "example_index": 0, "raw_html_path": "raw/entries/dbc809a94f2a02186c043000116cc9c59627c1ea6befb03ef881daa7ceec894d.html", "raw_html_sha256": "42c38fe65d661f2a6522dc2490573e2f8f88ecc0f9c30364632ae3ccc1549ad4", "fetched_at": "2026-07-12T02:47:36.840Z", "recordings": [ { "recording_id": "141fdd826bdabd8b3b3f942a7344ec3e1909748a1281e3842f10144f5a487aca", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/264/2647cd9e98476d003b901403a0a7abefdf0897a6629bc09b8438783c9e652834.mp3", "archive_relative_path": "raw/audio/264/2647cd9e98476d003b901403a0a7abefdf0897a6629bc09b8438783c9e652834.mp3" } ] } ], "prediction": "Amujpa etlmisga'latl.", "reference": "Wipit gesnuwaj." }, { "id": "mic-sent-b069ac8308f324018a6c8f9d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The poor cat is full of burdocks.", "output_text": "Ewuljewe'jit gajuewj waju'et gesaluejijig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The poor cat is full of burdocks.", "mic_Latn": "Ewuljewe'jit gajuewj waju'et gesaluejijig." }, "canonical_ref": "entries/g/gesaluejijit/gesaluejijit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7d24d46279d502ad5800", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesaluejijit/gesaluejijit.html", "entry_url": "https://mikmaqonline.org/entries/g/gesaluejijit/gesaluejijit.html", "headword": "gesaluejijit", "example_index": 0, "raw_html_path": "raw/entries/94d9a43db7ab33568310339ad26d7855ce963aeed18b68406803d80a06c21ac5.html", "raw_html_sha256": "555acd130caba3510d0a9de887b5a5faa125399a42e9a4408e3d1b136a193594", "fetched_at": "2026-07-12T02:39:02.700Z", "recordings": [ { "recording_id": "81a8454099ebb5218aaa4be3ae0d505b2ebd4110e4c351a843e2a241ce3714d9", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ffb/ffb42c203d985d2305d4b855efc8f6caf3daa648a766f898bbcf59362863b3c3.mp3", "archive_relative_path": "raw/audio/ffb/ffb42c203d985d2305d4b855efc8f6caf3daa648a766f898bbcf59362863b3c3.mp3" } ] } ], "prediction": "Pilei gajuewji'j gaqate'g.", "reference": "Ewuljewe'jit gajuewj waju'et gesaluejijig." }, { "id": "mic-sent-b0e2cd815de74016c6ea76f0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My niece has twins.", "output_text": "Nsm (g)eggunajig tqope'jg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My niece has twins.", "mic_Latn": "Nsm (g)eggunajig tqope'jg." }, "canonical_ref": "entries/t/tqope'j/tqope'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4ad84be8de682537f0b8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tqope'j/tqope'j.html", "entry_url": "https://mikmaqonline.org/entries/t/tqope'j/tqope'j.html", "headword": "tqope'j", "example_index": 0, "raw_html_path": "raw/entries/a6a69bd673136bbccf3305047b00ad5bf0a78c2f11342837a4777f284046ff95.html", "raw_html_sha256": "718a120bd6395d049a896f4234f1296939743d6b04833093e0f17833acf72a89", "fetched_at": "2026-07-12T02:46:06.484Z", "recordings": [ { "recording_id": "bdb1d08017d464a5df348774b0d42db6c2fb3a5a13bd63062fc9baf34abe55cc", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9d3/9d34321b64ecf49d7cef68bde6e6b39568754b7821e9d10c4cdc60c33b4ccfc9.mp3", "archive_relative_path": "raw/audio/9d3/9d34321b64ecf49d7cef68bde6e6b39568754b7821e9d10c4cdc60c33b4ccfc9.mp3" } ] } ], "prediction": "Nuji'j na gmu'jig.", "reference": "Nsm (g)eggunajig tqope'jg." }, { "id": "mic-sent-b0f73c8f9147388001e52781:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He's happy about his new blue vehicle.", "output_text": "Welta'suatg na pilei ewne'g utepaqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He's happy about his new blue vehicle.", "mic_Latn": "Welta'suatg na pilei ewne'g utepaqan." }, "canonical_ref": "entries/w/welta'suatg/welta'suatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-57efa1ce1eb4e32c8394", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/welta'suatg/welta'suatg.html", "entry_url": "https://mikmaqonline.org/entries/w/welta'suatg/welta'suatg.html", "headword": "welta'suatg", "example_index": 0, "raw_html_path": "raw/entries/756a34bed0bad80ae5e1a04bffa2a62a11cc7f22b4d54e4e2fa2659dd40aa477.html", "raw_html_sha256": "72513b0d27de3dc88cb8b844628d69b56b5d658685f2dda65e6b38838107143f", "fetched_at": "2026-07-12T02:47:09.409Z", "recordings": [ { "recording_id": "f38a915c02955c69305014790e9fc25e005269b53375db250b7161e0353880c0", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bbc/bbcafd82ed0b8eb1b05c9570d7757e3f225431434befad1df61c69aa8c060c76.mp3", "archive_relative_path": "raw/audio/bbc/bbcafd82ed0b8eb1b05c9570d7757e3f225431434befad1df61c69aa8c060c76.mp3" } ] } ], "prediction": "Pugwelg na utepaqan ugjit.", "reference": "Welta'suatg na pilei ewne'g utepaqan." }, { "id": "mic-sent-b1527b8e6413584794dbf715:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "For now it is stopped, but we are trying to fix it.", "output_text": "Pe'l nige' enqateg, gatu wejo'tmeg lugwatmnen.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "For now it is stopped, but we are trying to fix it.", "mic_Latn": "Pe'l nige' enqateg, gatu wejo'tmeg lugwatmnen." }, "canonical_ref": "entries/e/enqateg/enqateg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-06ca574e80c094d40261", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/enqateg/enqateg.html", "entry_url": "https://mikmaqonline.org/entries/e/enqateg/enqateg.html", "headword": "enqateg", "example_index": 0, "raw_html_path": "raw/entries/7e789d9637d445cbdb18f82afc2834c6a9f4bce3480e041743b626a499553c1d.html", "raw_html_sha256": "30a35a80f7b831d02f641269213cc9481816de83496de417f4fe9e4dc989462f", "fetched_at": "2026-07-12T02:38:06.110Z", "recordings": [ { "recording_id": "7d68b41bd1af2f5ee4c7a087d17bcc090494248b5285eed9efef53dbee5f8fb3", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b76/b7609891899728c5c4163c6657a3652e8497f0d9117f0af2f00fc6e220a0e795.mp3", "archive_relative_path": "raw/audio/b76/b7609891899728c5c4163c6657a3652e8497f0d9117f0af2f00fc6e220a0e795.mp3" } ] } ], "prediction": "Ge's nige' gesatg, gatu poqji'jig.", "reference": "Pe'l nige' enqateg, gatu wejo'tmeg lugwatmnen." }, { "id": "mic-sent-b197a8e78339b975de160f4f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where do birch genus trees grow?", "output_text": "Tami nigwejig masgwe'simusi'g?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where do birch genus trees grow?", "mic_Latn": "Tami nigwejig masgwe'simusi'g?" }, "canonical_ref": "entries/m/masgwe'simusi/masgwe'simusi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-731e6b5b91f7dc9d5952", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/masgwe'simusi/masgwe'simusi.html", "entry_url": "https://mikmaqonline.org/entries/m/masgwe'simusi/masgwe'simusi.html", "headword": "masgwe'simusi", "example_index": 0, "raw_html_path": "raw/entries/19e4ca3f46c5c7460bcf807b62b7d850f7c4ff66fe234ca8d7d402c36edc282c.html", "raw_html_sha256": "d41095c3051e125c207e879cbeb003436ac3f712dd4931a77799e99b734722c8", "fetched_at": "2026-07-12T02:40:52.853Z", "recordings": [ { "recording_id": "be6434d77c22b4e3bbf99bd0dbaf56522494824c4b6aded0e3db72f5792b0e3f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2e3/2e385685cbf2c2514a74f0f2995b55c643e279c0b4ba5ad7795275994370b9e5.mp3", "archive_relative_path": "raw/audio/2e3/2e385685cbf2c2514a74f0f2995b55c643e279c0b4ba5ad7795275994370b9e5.mp3" } ] } ], "prediction": "Tami we'gwi'g wi'jig?", "reference": "Tami nigwejig masgwe'simusi'g?" }, { "id": "mic-sent-b1b1a5f714e25abd5fbc484b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The children drag out a long timber, they are apparently planning to build a little play house.", "output_text": "Mijua'jijg tewatejima'titl tilsl, wenji'guomji'j toqo eltu'tij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The children drag out a long timber, they are apparently planning to build a little play house.", "mic_Latn": "Mijua'jijg tewatejima'titl tilsl, wenji'guomji'j toqo eltu'tij." }, "canonical_ref": "entries/t/tewatejimatl/tewatejimatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4c1684185238f0e405ca", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tewatejimatl/tewatejimatl.html", "entry_url": "https://mikmaqonline.org/entries/t/tewatejimatl/tewatejimatl.html", "headword": "tewatejimatl", "example_index": 0, "raw_html_path": "raw/entries/c6fb668f2b846954a268e846cb01e5dbfd27a607ca0cb54831664a720f5de58e.html", "raw_html_sha256": "a1fcea32228274af3ad1db464304076041ca9ca5d8c5f0eded1e87a5b721d63d", "fetched_at": "2026-07-12T02:45:53.517Z", "recordings": [ { "recording_id": "e83f18782bd2c2ccaa58c90294523837cd6abaf1c472d8e69af2b4c7913342ea", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a5d/a5d834052a48f8c82136369c450b4ecedb891828ae84891269e1ad4415f4d65c.mp3", "archive_relative_path": "raw/audio/a5d/a5d834052a48f8c82136369c450b4ecedb891828ae84891269e1ad4415f4d65c.mp3" } ] } ], "prediction": "Lpa'tu'ji'jig lpa'tmu'jg, na'te's'g'p't'p na'qwanigtug.", "reference": "Mijua'jijg tewatejima'titl tilsl, wenji'guomji'j toqo eltu'tij." }, { "id": "mic-sent-b34023e103af37ab7115061f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Sometimes one gets drowsy in the middle of the day.", "output_text": "Jijuaqa wen miawna'gweg getugsiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Sometimes one gets drowsy in the middle of the day.", "mic_Latn": "Jijuaqa wen miawna'gweg getugsiet." }, "canonical_ref": "entries/g/getugsiet/getugsiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-25257d8d5e5921b747d9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/getugsiet/getugsiet.html", "entry_url": "https://mikmaqonline.org/entries/g/getugsiet/getugsiet.html", "headword": "getugsiet", "example_index": 0, "raw_html_path": "raw/entries/279e2c001806c560c8f77bb03f1c4f51541aee64025f70371fbae547cc2da3e3.html", "raw_html_sha256": "894f8abf7df96d57ddcca763315190502f0e00ddd29e62ad2e70ce511c1985c4", "fetched_at": "2026-07-12T02:39:24.699Z", "recordings": [ { "recording_id": "6bb85fdee373dea90d0fd894d9509a5cb137c478a8909a437907b00c160c729d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/db1/db10e6965f15557c6228fede432f898dd9d04f88c068767abe921e966c227d37.mp3", "archive_relative_path": "raw/audio/db1/db10e6965f15557c6228fede432f898dd9d04f88c068767abe921e966c227d37.mp3" } ] } ], "prediction": "We'gwi'g newte's'g ta'n te'sipu'g.", "reference": "Jijuaqa wen miawna'gweg getugsiet." }, { "id": "mic-sent-b3704c7a5c16e299dcd0714f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Tio'tis is satisfied with her new pen.", "output_text": "Tio'tis migua'latl pile'l wi'gignml.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Tio'tis is satisfied with her new pen.", "mic_Latn": "Tio'tis migua'latl pile'l wi'gignml." }, "canonical_ref": "entries/m/migua'latl/migua'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2185bd0d2cfe0e836935", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/migua'latl/migua'latl.html", "entry_url": "https://mikmaqonline.org/entries/m/migua'latl/migua'latl.html", "headword": "migua'latl", "example_index": 0, "raw_html_path": "raw/entries/67bd7159d6270356d87bb97f4c124fac15a26f9278d95b01dd38db6980097ab0.html", "raw_html_sha256": "61023ce884863cca70f21f09455967a4479ffd2846e4fd70dcf2870d439cfba9", "fetched_at": "2026-07-12T02:41:33.441Z", "recordings": [ { "recording_id": "9f2cfd316d5277a67085148f6c293623145184c020495733380c90fbaf2f8818", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ea7/ea711884ff3c553384d2dd11766eddfec1b8e3542b0a3c39975c40838078e879.mp3", "archive_relative_path": "raw/audio/ea7/ea711884ff3c553384d2dd11766eddfec1b8e3542b0a3c39975c40838078e879.mp3" } ] } ], "prediction": "Tio'tis gesatg ugjit ugjitl ugtaqan.", "reference": "Tio'tis migua'latl pile'l wi'gignml." }, { "id": "mic-sent-b426d7917dad0035a822472f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Finally my dog is maturing.", "output_text": "Glapis gatu nti nestu'et.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Finally my dog is maturing.", "mic_Latn": "Glapis gatu nti nestu'et." }, "canonical_ref": "entries/n/nestu'et/nestu'et.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6428025caf23920ca4dd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nestu'et/nestu'et.html", "entry_url": "https://mikmaqonline.org/entries/n/nestu'et/nestu'et.html", "headword": "nestu'et", "example_index": 0, "raw_html_path": "raw/entries/92803ce3c98fa664f1a2e4996378d24a828e760595ebc8e15be30261f60ba50f.html", "raw_html_sha256": "f49aa252222ab79bf36d98d271bfa14cecbf6d36d9b6a475197a808838402162", "fetched_at": "2026-07-12T02:42:23.751Z", "recordings": [ { "recording_id": "0c58ab4e652ac67e577e9e31ebbade25e8c28cb7623c1e33dfab3e947364240c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6e5/6e53f2d0d0540afe78442a1347abadfb539a5cd0cea94cd6a318cbb3d32da61a.mp3", "archive_relative_path": "raw/audio/6e5/6e53f2d0d0540afe78442a1347abadfb539a5cd0cea94cd6a318cbb3d32da61a.mp3" } ] } ], "prediction": "Gi's gi's nmuji'j nmu'j gesatg.", "reference": "Glapis gatu nti nestu'et." }, { "id": "mic-sent-b4c3f417dbc53c672021acf2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she cries whenever he/she has weird dreams.", "output_text": "Atgitemit ta'n tujiw milpuwitegej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she cries whenever he/she has weird dreams.", "mic_Latn": "Atgitemit ta'n tujiw milpuwitegej." }, "canonical_ref": "entries/a/atgitemit/atgitemit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-975f2c5de09625631b32", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/atgitemit/atgitemit.html", "entry_url": "https://mikmaqonline.org/entries/a/atgitemit/atgitemit.html", "headword": "atgitemit", "example_index": 0, "raw_html_path": "raw/entries/5944481c3652435c7af2b74a1647cd8af4ce79de14e51d82da6cd40153b03c8c.html", "raw_html_sha256": "9e7365a7142f23489eb4e8b6d88596027adf1ed3e62bac42c3d4aad30cb624a9", "fetched_at": "2026-07-12T02:37:24.533Z", "recordings": [ { "recording_id": "9f4187f55ab9bfd3cedd53e2134295c8d190298f045f3c93a49e2c4546a178f6", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/826/8265c7f8810993ff1a9395570f03cba0378378a8af4cfe336be70dffe7aea25a.mp3", "archive_relative_path": "raw/audio/826/8265c7f8810993ff1a9395570f03cba0378378a8af4cfe336be70dffe7aea25a.mp3" } ] } ], "prediction": "Te's'g we'gwi'g ta'n tujiw wejoqwei.", "reference": "Atgitemit ta'n tujiw milpuwitegej." }, { "id": "mic-sent-b4ccaae8cfbc957725805457:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Peter's job, now he does different work.", "output_text": "Pie'l ugtlugowaqan, na nige' piltu'lugwet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Peter's job, now he does different work.", "mic_Latn": "Pie'l ugtlugowaqan, na nige' piltu'lugwet." }, "canonical_ref": "entries/p/piltu'lugwet/piltu'lugwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0fbc4c0d5e9d9fb2a916", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/piltu'lugwet/piltu'lugwet.html", "entry_url": "https://mikmaqonline.org/entries/p/piltu'lugwet/piltu'lugwet.html", "headword": "piltu'lugwet", "example_index": 0, "raw_html_path": "raw/entries/f0f567a98a4717485a993cd24a9035413be7178bf66a092e50c3426b4b64393e.html", "raw_html_sha256": "c073ce4ca35f0fe7d35ecb33afb6f3204a789c83962199120ae284d57a1a9462", "fetched_at": "2026-07-12T02:43:58.545Z", "recordings": [ { "recording_id": "e118d5f136b42f451abc73829ac2dbd1d09664faa60d4fb3b52b145d6a20533f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ae4/ae4487f41efecf2e4766fc4a660c63071a5078b9a33ee80908929c99178dd9d7.mp3", "archive_relative_path": "raw/audio/ae4/ae4487f41efecf2e4766fc4a660c63071a5078b9a33ee80908929c99178dd9d7.mp3" } ] } ], "prediction": "Pie'l na'te'l, nige' negm newtegetl.", "reference": "Pie'l ugtlugowaqan, na nige' piltu'lugwet." }, { "id": "mic-sent-b4ee470bb74259147500f050:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she isn't lying down anymore, he/she is standing.", "output_text": "Mu' nugu' elisinug, menj'puguit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she isn't lying down anymore, he/she is standing.", "mic_Latn": "Mu' nugu' elisinug, menj'puguit." }, "canonical_ref": "entries/m/menj'puguit/menj'puguit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ddf632798cdfac13a216", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/menj'puguit/menj'puguit.html", "entry_url": "https://mikmaqonline.org/entries/m/menj'puguit/menj'puguit.html", "headword": "menj'puguit", "example_index": 0, "raw_html_path": "raw/entries/2f78e090612b31f89a8f4d76feb1a975bd59ee04f9a1160bd81d6266ed1ea08b.html", "raw_html_sha256": "2af2ef58326497b0f22b867589cfc6272b80bf9cf643cc2e2bb0c2ea36e7021c", "fetched_at": "2026-07-12T02:41:17.812Z", "recordings": [ { "recording_id": "af96e1409de2fc2a71f4e2f461e35798cccb7bcb264392ea31cafacec7a0bf2c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5f5/5f58996d187d5e1e0ed354936537cb12cf820ef306d2a34210317aa4f987c020.mp3", "archive_relative_path": "raw/audio/5f5/5f58996d187d5e1e0ed354936537cb12cf820ef306d2a34210317aa4f987c020.mp3" } ] } ], "prediction": "Ma' nugu' ni'n gisga'sit, lugowa'sit.", "reference": "Mu' nugu' elisinug, menj'puguit." }, { "id": "mic-sent-b55175315d9d9e7515a26be6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Is your vehicle straight?", "output_text": "Tetpaqteg na gutepaqan?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Is your vehicle straight?", "mic_Latn": "Tetpaqteg na gutepaqan?" }, "canonical_ref": "entries/t/tetpaqteg/tetpaqteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a6acb443a3bd1095ee26", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tetpaqteg/tetpaqteg.html", "entry_url": "https://mikmaqonline.org/entries/t/tetpaqteg/tetpaqteg.html", "headword": "tetpaqteg", "example_index": 0, "raw_html_path": "raw/entries/24cfcd6b88617cb7b60939b60e26328d3d383930c66687042089b3489678aaec.html", "raw_html_sha256": "7578cc6dd8c36531af206ac4ad8076521c4d6484ea870de8f71acf3b0e333e42", "fetched_at": "2026-07-12T02:45:51.103Z", "recordings": [ { "recording_id": "3e65867c15a1bddbc1421379bd3ff658bca2911e6660e912386e06dc570ab975", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7db/7db391128d73e5f4119ad22d49967067efa80ee450cd52c54df769b3c155ce78.mp3", "archive_relative_path": "raw/audio/7db/7db391128d73e5f4119ad22d49967067efa80ee450cd52c54df769b3c155ce78.mp3" } ] } ], "prediction": "We'gwi'g na utepaqan?", "reference": "Tetpaqteg na gutepaqan?" }, { "id": "mic-sent-b5b2120aeaee99b3a6a094e2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When you plow, do you use a horse?", "output_text": "Elgesewen te'sipow e'w't?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When you plow, do you use a horse?", "mic_Latn": "Elgesewen te'sipow e'w't?" }, "canonical_ref": "entries/e/elgesawet/elgesawet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ae691b7d74e5a91eb5f5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elgesawet/elgesawet.html", "entry_url": "https://mikmaqonline.org/entries/e/elgesawet/elgesawet.html", "headword": "elgesawet", "example_index": 0, "raw_html_path": "raw/entries/75c9d3145f237506b6fc4d0f75497be77708a8a4ea6c0fd5eec46044097c13dd.html", "raw_html_sha256": "7ad7944432527d1d3cf6e8a1b30eec867f68f03755d33555eac4e9441c1bca32", "fetched_at": "2026-07-12T02:37:42.875Z", "recordings": [ { "recording_id": "2d4fabea7e449cb80df6419e1048b0a77ddd303678d421a4d67850b58ff1cb30", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/40b/40bbf64db4b9fd2119deadc3489960ad8978b24bd4d30eb35e5def63d172e479.mp3", "archive_relative_path": "raw/audio/40b/40bbf64db4b9fd2119deadc3489960ad8978b24bd4d30eb35e5def63d172e479.mp3" } ] } ], "prediction": "Ta'n ta'n tujiw gesatg, lpa ni'n te's'g?", "reference": "Elgesewen te'sipow e'w't?" }, { "id": "mic-sent-b60289de71f7b8c76553c26c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Peter finally stops living in the woods.", "output_text": "Pie'l nugu' punqatg nipugtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Peter finally stops living in the woods.", "mic_Latn": "Pie'l nugu' punqatg nipugtug." }, "canonical_ref": "entries/p/punqatg/punqatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-063041290927822325f5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/punqatg/punqatg.html", "entry_url": "https://mikmaqonline.org/entries/p/punqatg/punqatg.html", "headword": "punqatg", "example_index": 0, "raw_html_path": "raw/entries/0970ad73116596f90782742b70233aa7e24c02e854f886ec5a894cce4ad42d2f.html", "raw_html_sha256": "2094d2c29f8acee9e7a3c021b76479bf41b1ee229ac6c5d99b98abf8d35196dd", "fetched_at": "2026-07-12T02:44:27.289Z", "recordings": [ { "recording_id": "e82e9b011c7f5efee5adbae16e6f8c0597701d632d8d12feed96a651faadd1a6", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/486/48620d7f084ebfc2e52c86d4c6e8f40ec11e636aa110efd805f7ceadd6855c4d.mp3", "archive_relative_path": "raw/audio/486/48620d7f084ebfc2e52c86d4c6e8f40ec11e636aa110efd805f7ceadd6855c4d.mp3" } ] } ], "prediction": "Pie'l gi's gaqama'toq ugjit.", "reference": "Pie'l nugu' punqatg nipugtug." }, { "id": "mic-sent-b61afec0fcce792280bf7f1a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she puts raspberries on their breakfast.", "output_text": "Epiga'laji gmu'jming ugegsitpu'goweimg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she puts raspberries on their breakfast.", "mic_Latn": "Epiga'laji gmu'jming ugegsitpu'goweimg." }, "canonical_ref": "entries/e/epiga'latl/epiga'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-527c5644b3ca06eff236", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/epiga'latl/epiga'latl.html", "entry_url": "https://mikmaqonline.org/entries/e/epiga'latl/epiga'latl.html", "headword": "epiga'latl", "example_index": 0, "raw_html_path": "raw/entries/145e941258101cc29f487d660275a72172ad7fbe28fdadd8894d766c3c2d0775.html", "raw_html_sha256": "1d478543d4b4fbb58607c63660ecbcf63b11cde84427a01da683a83270813b1e", "fetched_at": "2026-07-12T02:36:19.302Z", "recordings": [ { "recording_id": "7fbb79780045ec4b34846408087b4ae4a15fef9bb95ac1ebf5f839192f389ab3", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/615/61546103c3328bc4261c84d15ecc6561e4b80ad86c338079ea546c41b7f460a2.mp3", "archive_relative_path": "raw/audio/615/61546103c3328bc4261c84d15ecc6561e4b80ad86c338079ea546c41b7f460a2.mp3" } ] } ], "prediction": "Pugwelga'latl ugjit ugjit.", "reference": "Epiga'laji gmu'jming ugegsitpu'goweimg." }, { "id": "mic-sent-b63a7e1262545eb27d895da5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she gathered provisions for three days before he/she left.", "output_text": "Nesuguna'q netugulip gesgmnaq maja'sigweg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she gathered provisions for three days before he/she left.", "mic_Latn": "Nesuguna'q netugulip gesgmnaq maja'sigweg." }, "canonical_ref": "entries/n/netugulit/netugulit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-99a55e36ad69390a2677", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/netugulit/netugulit.html", "entry_url": "https://mikmaqonline.org/entries/n/netugulit/netugulit.html", "headword": "netugulit", "example_index": 0, "raw_html_path": "raw/entries/fffd51c350c19db50b941faee3a781e0a39052bc146538f5eb93ff9b3b1b777e.html", "raw_html_sha256": "d2eafdcb184f7b9fc2d4bf96a401674a24ac46a31eee98ffb41798472ffc11d0", "fetched_at": "2026-07-12T02:42:25.679Z", "recordings": [ { "recording_id": "e2d2d417a716e615d434fa7dab155e5eb9cb9f4c441bfd334935255ca3bc4eff", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e1e/e1e68ab74bdd2d28d8d379722be39487d23cfe5bfdce6841e984449ddc723061.mp3", "archive_relative_path": "raw/audio/e1e/e1e68ab74bdd2d28d8d379722be39487d23cfe5bfdce6841e984449ddc723061.mp3" } ] } ], "prediction": "Te's'g wasqo'toq te'sipu'g gesgmnaq gisijg.", "reference": "Nesuguna'q netugulip gesgmnaq maja'sigweg." }, { "id": "mic-sent-b824ae52e8f05cea50b4c84e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This sews and at the same time counts how many are made.", "output_text": "Ula eli'seweg aq nespilugweg etlgitg ta'n te's'g eltas'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This sews and at the same time counts how many are made.", "mic_Latn": "Ula eli'seweg aq nespilugweg etlgitg ta'n te's'g eltas'g." }, "canonical_ref": "entries/n/nespilugweg/nespilugweg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3bb8d6918eddcf81278b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nespilugweg/nespilugweg.html", "entry_url": "https://mikmaqonline.org/entries/n/nespilugweg/nespilugweg.html", "headword": "nespilugweg", "example_index": 0, "raw_html_path": "raw/entries/53c8dc5f930637796db271be7184883c4fa77ad931d9b7d21f5efa6b9539c3a2.html", "raw_html_sha256": "ff29d550ffe8a4c2360ca7b650d7b053419de1e84ec76e18323e56c81426479e", "fetched_at": "2026-07-12T02:42:22.545Z", "recordings": [ { "recording_id": "2cfbbc68fd5dec1bb56e57779f255456241665cda095daa89400777426eec994", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e88/e88e1de3430a17c1616d8bb17e22898edcd109c7c17e628d115acf3509bdc1b8.mp3", "archive_relative_path": "raw/audio/e88/e88e1de3430a17c1616d8bb17e22898edcd109c7c17e628d115acf3509bdc1b8.mp3" } ] } ], "prediction": "Ula na'te'g aq ta'n tujiw telta'toq te'sijig.", "reference": "Ula eli'seweg aq nespilugweg etlgitg ta'n te's'g eltas'g." }, { "id": "mic-sent-b83a84d178c0d292fd07d3db:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Have you been to the First District?", "output_text": "Gi's gi'l Gespogwitg wejien?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Have you been to the First District?", "mic_Latn": "Gi's gi'l Gespogwitg wejien?" }, "canonical_ref": "entries/g/Gespogwitg/Gespogwitg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-454aff8e18cee9ad2b22", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/Gespogwitg/Gespogwitg.html", "entry_url": "https://mikmaqonline.org/entries/g/Gespogwitg/Gespogwitg.html", "headword": "Gespogwitg", "example_index": 0, "raw_html_path": "raw/entries/813537831c714b1f4b5ffd8a3db53da9ff6bd230233828d160f8d0d13495e737.html", "raw_html_sha256": "4d8fdc08ef054963568aeb78d03a159772d44524243d9ec92fc89c850f92279e", "fetched_at": "2026-07-12T02:39:18.472Z", "recordings": [ { "recording_id": "39ca45e735ba149e4912c1241cabf819b84325b0b9f9f0642ff3e1a5d90d26e7", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/782/78228bf97072f9f3b4dff48bdb85a8ebe63f525f8638e686ea93bd6613082096.mp3", "archive_relative_path": "raw/audio/782/78228bf97072f9f3b4dff48bdb85a8ebe63f525f8638e686ea93bd6613082096.mp3" } ] } ], "prediction": "Gi's gi'l We'gwig?", "reference": "Gi's gi'l Gespogwitg wejien?" }, { "id": "mic-sent-b89ed14449d7b06fb24e4d14:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The young man is taking care of his baby for the first time.", "output_text": "Ji'nmji'j amgwes naqanu'salatl unjann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The young man is taking care of his baby for the first time.", "mic_Latn": "Ji'nmji'j amgwes naqanu'salatl unjann." }, "canonical_ref": "entries/n/naqanu'set/naqanu'set.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-93b75603dca341a7ab61", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/naqanu'set/naqanu'set.html", "entry_url": "https://mikmaqonline.org/entries/n/naqanu'set/naqanu'set.html", "headword": "naqanu'set", "example_index": 0, "raw_html_path": "raw/entries/96c45abd6f368777ccba941f35cde2f6f3abede26e67b024aba9d2e5de539fd1.html", "raw_html_sha256": "5d44ad1999fd08512cf3c04fcb463e114533d78cf316715f40e4cf1819106f01", "fetched_at": "2026-07-12T02:42:03.028Z", "recordings": [ { "recording_id": "3f890b7efba75fd61b6af4336052cb14b3f03a0c220df4acb352a0e36c4f117b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bd6/bd602397c99d2fe730eb2c6323cd82ed4ecdf97fd47909f7f175fd59cce59324.mp3", "archive_relative_path": "raw/audio/bd6/bd602397c99d2fe730eb2c6323cd82ed4ecdf97fd47909f7f175fd59cce59324.mp3" } ] } ], "prediction": "Lpa'tuj angua'latl unjann.", "reference": "Ji'nmji'j amgwes naqanu'salatl unjann." }, { "id": "mic-sent-b90ec22ae34301799aa96a82:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is in a hurry for the week to be over because on Saturday they are leaving on a trip.", "output_text": "Nenaq'te'tg aqantie'uti gaqian muta Gesp'teg poqtamgita'jig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is in a hurry for the week to be over because on Saturday they are leaving on a trip.", "mic_Latn": "Nenaq'te'tg aqantie'uti gaqian muta Gesp'teg poqtamgita'jig." }, "canonical_ref": "entries/n/nenaqite'tg/nenaqite'tg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-13152a63d7ff81bd16c0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nenaqite'tg/nenaqite'tg.html", "entry_url": "https://mikmaqonline.org/entries/n/nenaqite'tg/nenaqite'tg.html", "headword": "nenaqite'tg", "example_index": 0, "raw_html_path": "raw/entries/1b4e132e2637eebe72107e3a6eff4fce52c9b7c1ae9b97ffda6d6884898b2add.html", "raw_html_sha256": "004e7b0149af3195eab21f20350adaa3af9c78edcf15aaf58b1422d068af1281", "fetched_at": "2026-07-12T02:42:18.615Z", "recordings": [ { "recording_id": "2dd5d5f6c26d32be6ceb23ea7eb40749c959cfb0b4491e2d0cef6cec487e9be1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/52d/52dfdef724330365c8fa9f94dd80e252b8c27c52c35659001e9c78fb76d13568.mp3", "archive_relative_path": "raw/audio/52d/52dfdef724330365c8fa9f94dd80e252b8c27c52c35659001e9c78fb76d13568.mp3" } ] } ], "prediction": "Pugwelg'g ta'n te'sipu'g muta te's'g na'te'g.", "reference": "Nenaq'te'tg aqantie'uti gaqian muta Gesp'teg poqtamgita'jig." }, { "id": "mic-sent-b97567a968dc0b7433df7e89:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is using a gun to shoot at a bottle.", "output_text": "Pe'sgewei e'w'g pu'tail matteluatl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is using a gun to shoot at a bottle.", "mic_Latn": "Pe'sgewei e'w'g pu'tail matteluatl." }, "canonical_ref": "entries/m/matteluatl/matteluatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dcd5dd7d013e066645c2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/matteluatl/matteluatl.html", "entry_url": "https://mikmaqonline.org/entries/m/matteluatl/matteluatl.html", "headword": "matteluatl", "example_index": 0, "raw_html_path": "raw/entries/eb1e94531af384ed6e54f853fd37737283ee3816c7dfa2c276cff16719b566af.html", "raw_html_sha256": "10230ae1da6a8fe5c2df93823d6b447b41a75fb4545fa161a979e05b2a05a955", "fetched_at": "2026-07-12T02:40:56.694Z", "recordings": [ { "recording_id": "0f23f01caab4f64a760fae31a04fd2d35aec51071ba75c49ab018d08f85c0d1a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6d7/6d70c52315497a4c5b01ba04170cc1615ec7929482ce9301c7a1f0407caca996.mp3", "archive_relative_path": "raw/audio/6d7/6d70c52315497a4c5b01ba04170cc1615ec7929482ce9301c7a1f0407caca996.mp3" } ] } ], "prediction": "Ugo'toq ugta'latl ugtaqanigtug.", "reference": "Pe'sgewei e'w'g pu'tail matteluatl." }, { "id": "mic-sent-ba1d2b02d3c06210287483eb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Buy six white ankle length socks.", "output_text": "As'gom te's'gl sigsuti'l wape'gl pgwatele'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Buy six white ankle length socks.", "mic_Latn": "As'gom te's'gl sigsuti'l wape'gl pgwatele'n." }, "canonical_ref": "entries/s/sigsuti/sigsuti.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8b2daf368c30d996e7a8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sigsuti/sigsuti.html", "entry_url": "https://mikmaqonline.org/entries/s/sigsuti/sigsuti.html", "headword": "sigsuti", "example_index": 0, "raw_html_path": "raw/entries/19d2e3c7c072b009f9c93ca325ef67110839b516382dc909abf35cfdf3d440ea.html", "raw_html_sha256": "b7cda6a5abdc5f8bad8ad939ff0dfb63a22e158ce1b237abb9c75edb9789f42e", "fetched_at": "2026-07-12T02:45:00.941Z", "recordings": [ { "recording_id": "af2025eed12eb6e04d18e1bc3789ef20650dfc58e3ff94af5e6e734a73f43b3d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5f2/5f2717d80276f4f019a07213c91d856fc3434581d7702e8c610e8119352fe5a2.mp3", "archive_relative_path": "raw/audio/5f2/5f2717d80276f4f019a07213c91d856fc3434581d7702e8c610e8119352fe5a2.mp3" } ] } ], "prediction": "Amujpa etlmisga'toq ga'qanigtug.", "reference": "As'gom te's'gl sigsuti'l wape'gl pgwatele'n." }, { "id": "mic-sent-ba3938b34a0650929c5b28c3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Every time the pail runs dry, fill it up again.", "output_text": "Te's la'taqsun niwa'sij ap ugju'pega'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Every time the pail runs dry, fill it up again.", "mic_Latn": "Te's la'taqsun niwa'sij ap ugju'pega'l." }, "canonical_ref": "entries/n/niwa'sit/niwa'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b807f4902413e81b3b2a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/niwa'sit/niwa'sit.html", "entry_url": "https://mikmaqonline.org/entries/n/niwa'sit/niwa'sit.html", "headword": "niwa'sit", "example_index": 0, "raw_html_path": "raw/entries/b9f4d7335bd2f4e6f6d6d2676f929a3ffc6cb44a498a28e34b4452bbdc6b2a1f.html", "raw_html_sha256": "554627a1762456cbb8c2c536095e5de9a41475810a467794f3f8a57eae7b96a0", "fetched_at": "2026-07-12T02:42:39.128Z", "recordings": [ { "recording_id": "c15167f752dcae3401c53713edd5fb760a37c2db483811690ce6906064145fde", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e7d/e7dfc7f0b06cdda599ee2bdc859247e447c052cc8f782f5a85d58c5f139feb53.mp3", "archive_relative_path": "raw/audio/e7d/e7dfc7f0b06cdda599ee2bdc859247e447c052cc8f782f5a85d58c5f139feb53.mp3" } ] } ], "prediction": "Te's ta'n te's'g wi'gwi'g, newtepa'toq.", "reference": "Te's la'taqsun niwa'sij ap ugju'pega'l." }, { "id": "mic-sent-ba74872f7d2c03695f3b8346:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I found my keys, they were here in full view.", "output_text": "We'jituann ntap'sqi'gnml, ula me'su'tug eteg'snn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I found my keys, they were here in full view.", "mic_Latn": "We'jituann ntap'sqi'gnml, ula me'su'tug eteg'snn." }, "canonical_ref": "entries/m/me'su'tug/me'su'tug.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8d836bcc89c28de46a66", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/me'su'tug/me'su'tug.html", "entry_url": "https://mikmaqonline.org/entries/m/me'su'tug/me'su'tug.html", "headword": "me'su'tug", "example_index": 0, "raw_html_path": "raw/entries/1eb184e860d872a68872e438e332168c0bac94478c8583e1ebdde37cf1cba8e0.html", "raw_html_sha256": "521d60436383dffde6b0ff92155fc8c7019c61ea7671758f644b70d4a2d3d314", "fetched_at": "2026-07-12T02:41:24.419Z", "recordings": [ { "recording_id": "d58b731b1c0918822caae844d22b097a866ef7f9105458663de771d1c626c59f", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c2d/c2d332ca3dffdf848a3fb955663fde70d1b70596dc206a4761f0a310d2a6cb89.mp3", "archive_relative_path": "raw/audio/c2d/c2d332ca3dffdf848a3fb955663fde70d1b70596dc206a4761f0a310d2a6cb89.mp3" } ] } ], "prediction": "Nujua'toq ntusign, na ula tet.", "reference": "We'jituann ntap'sqi'gnml, ula me'su'tug eteg'snn." }, { "id": "mic-sent-bb48c458720857e5e8b436fa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The ice goes out in the spring.", "output_text": "Siggw enmitg mgumi.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The ice goes out in the spring.", "mic_Latn": "Siggw enmitg mgumi." }, "canonical_ref": "entries/e/enmitg/enmitg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f7e1e86541395037fefe", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/enmitg/enmitg.html", "entry_url": "https://mikmaqonline.org/entries/e/enmitg/enmitg.html", "headword": "enmitg", "example_index": 0, "raw_html_path": "raw/entries/0ef2e958525134f33ddba95d89ac7700b65846909ce792531de4340854a168f3.html", "raw_html_sha256": "d89fbd9cace595bfaea21159d915251cf724e63a7682481ea6c6eb46b6efd262", "fetched_at": "2026-07-12T02:38:03.291Z", "recordings": [ { "recording_id": "540186b35dde7aaf44b28cba527ab78a33dd8e724f9f8886a3f424200885baa3", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2f1/2f19ac548a78510510d2be440498df001953398986c69c9b287f86dbc45569b3.mp3", "archive_relative_path": "raw/audio/2f1/2f19ac548a78510510d2be440498df001953398986c69c9b287f86dbc45569b3.mp3" } ] } ], "prediction": "Pilei'g na gmu'j.", "reference": "Siggw enmitg mgumi." }, { "id": "mic-sent-bbc17b1bbcce0e0d30b4bd20:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "While Mary was hurrying up, she fell.", "output_text": "Ge's Mali pemtetaqa'sit na nisiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "While Mary was hurrying up, she fell.", "mic_Latn": "Ge's Mali pemtetaqa'sit na nisiet." }, "canonical_ref": "entries/t/tetaqa'sit/tetaqa'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1877d27d06c929767374", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tetaqa'sit/tetaqa'sit.html", "entry_url": "https://mikmaqonline.org/entries/t/tetaqa'sit/tetaqa'sit.html", "headword": "tetaqa'sit", "example_index": 0, "raw_html_path": "raw/entries/939f01fde1d2e3376e3ddab1d73e37d7382d7e932b0ffab7d3d3232f763d372e.html", "raw_html_sha256": "5cc111c8df3d0bee20976801de518d5c31152a3b979b729801b8e6f0bda2da97", "fetched_at": "2026-07-12T02:45:48.393Z", "recordings": [ { "recording_id": "9b1db7781ac87d7cc6dd92f63c18c542b9c8a4965e6a9631145397a59477b1be", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/eb8/eb8fa87ff695811cb75cf048506450b3cdf97701183519030515f3208ef3a3f2.mp3", "archive_relative_path": "raw/audio/eb8/eb8fa87ff695811cb75cf048506450b3cdf97701183519030515f3208ef3a3f2.mp3" } ] } ], "prediction": "Gi's Mali gesatg, we'gwita'sit.", "reference": "Ge's Mali pemtetaqa'sit na nisiet." }, { "id": "mic-sent-bc1c7056843d9e6734af776b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she pays close attention to how he/she hoists everything aboard so nothings will fall off.", "output_text": "Gigjepugu'tg ms't goqwei ta'n telteppilg glaman ma mnja'qtnug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she pays close attention to how he/she hoists everything aboard so nothings will fall off.", "mic_Latn": "Gigjepugu'tg ms't goqwei ta'n telteppilg glaman ma mnja'qtnug." }, "canonical_ref": "entries/t/teppilg/teppilg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-94ec28d61f4e61e19a13", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/teppilg/teppilg.html", "entry_url": "https://mikmaqonline.org/entries/t/teppilg/teppilg.html", "headword": "teppilg", "example_index": 0, "raw_html_path": "raw/entries/d749c70aae8aca44fb5f53f8a0301ffecd1a1ff7564107a4b7ea81d407014b98.html", "raw_html_sha256": "2e011ff6af5b551073a70f3874ba3b56220661d602c5ccbb5b1056e596471481", "fetched_at": "2026-07-12T02:45:44.649Z", "recordings": [ { "recording_id": "bb9df5e7babe5498549598d4b3280f2c7e4b35de77cbf8e479d7c4ecef514504", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/250/25086c3bce94e13a14c3b1aee66ed93d2ba351d495c9a0d134de5dfc7e71c3a9.mp3", "archive_relative_path": "raw/audio/250/25086c3bce94e13a14c3b1aee66ed93d2ba351d495c9a0d134de5dfc7e71c3a9.mp3" } ] } ], "prediction": "Gi's gesatg ta'n tujiw gisipa'toq te's'g goqwei mu gisi'g.", "reference": "Gigjepugu'tg ms't goqwei ta'n telteppilg glaman ma mnja'qtnug." }, { "id": "mic-sent-bd07baa1263dae22438b455f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "In the spring one hears many a frog.", "output_text": "Siggw na gaqatepiet sqolj nutut.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "In the spring one hears many a frog.", "mic_Latn": "Siggw na gaqatepiet sqolj nutut." }, "canonical_ref": "entries/s/sqolj/sqolj.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c8e2c673397bb3f74c79", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sqolj/sqolj.html", "entry_url": "https://mikmaqonline.org/entries/s/sqolj/sqolj.html", "headword": "sqolj", "example_index": 0, "raw_html_path": "raw/entries/c16bb515de392970aa5669cb35cf2f3df4ff68db249d6ad9df292e0de5726ba5.html", "raw_html_sha256": "0fd52d5f2cb1f578214f927a2029f0fde154af6fee2a1bf807b6f31df4fb6ed5", "fetched_at": "2026-07-12T02:45:14.505Z", "recordings": [ { "recording_id": "15ac0e5749e91d76d209ada2fde5662222bfa4eccfeff4fbbe6d1d7a998ca501", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cff/cff2c03726737556265b7a56947c60d3c758e89d3b2d8f67270880cab6f0a7e4.mp3", "archive_relative_path": "raw/audio/cff/cff2c03726737556265b7a56947c60d3c758e89d3b2d8f67270880cab6f0a7e4.mp3" } ] } ], "prediction": "Pugwelg ta'n te'sijig wi'gwi'jig.", "reference": "Siggw na gaqatepiet sqolj nutut." }, { "id": "mic-sent-bd236ad6e2fd069969365843:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has been sobbing all evening.", "output_text": "Gi's newtiwela'gw ejgwe'mat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has been sobbing all evening.", "mic_Latn": "Gi's newtiwela'gw ejgwe'mat." }, "canonical_ref": "entries/e/ejgwe'mat/ejgwe'mat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-13718c208d1e11ffd8cb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/ejgwe'mat/ejgwe'mat.html", "entry_url": "https://mikmaqonline.org/entries/e/ejgwe'mat/ejgwe'mat.html", "headword": "ejgwe'mat", "example_index": 0, "raw_html_path": "raw/entries/3f721e008e8c7b26e7f800ed8d7add51d686bffea34ed0649a1f04a52b28fcd8.html", "raw_html_sha256": "07bac00ec6122b69f831d347a1e0d1ec1759b3854aa1b5fcce1d16206cc4f33f", "fetched_at": "2026-07-12T02:37:33.529Z", "recordings": [ { "recording_id": "91f8b05b9891210883951c8bb0b5775afba4fd2a9cf3b7aaa5ac44a09cfcf43d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9f6/9f69661ea960722b1c546d4a068189637e7b0972fc88aa18717b5c22ff74b139.mp3", "archive_relative_path": "raw/audio/9f6/9f69661ea960722b1c546d4a068189637e7b0972fc88aa18717b5c22ff74b139.mp3" } ] } ], "prediction": "Gi's gi's newte'g.", "reference": "Gi's newtiwela'gw ejgwe'mat." }, { "id": "mic-sent-bd6b4063c602962c45949eab:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Last night I dreamed of the Thunderer.", "output_text": "Wela'gwe'g pewi'g'p gaqtugwewe'sm.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Last night I dreamed of the Thunderer.", "mic_Latn": "Wela'gwe'g pewi'g'p gaqtugwewe'sm." }, "canonical_ref": "entries/g/gaqtugwewe'sm/gaqtugwewe'sm.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a0f834385c931f2c95ee", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gaqtugwewe'sm/gaqtugwewe'sm.html", "entry_url": "https://mikmaqonline.org/entries/g/gaqtugwewe'sm/gaqtugwewe'sm.html", "headword": "gaqtugwewe'sm", "example_index": 0, "raw_html_path": "raw/entries/8e74cde1158b72f18391c38ddc14ceae28b930ca7041da70b2e078f6a069b916.html", "raw_html_sha256": "89a03d173ba089ef2db92fbff5b6419640d9815ee6e18b994a7e576b0c3e1036", "fetched_at": "2026-07-12T02:38:43.308Z", "recordings": [ { "recording_id": "5846c6b5e9ec96a35db9603cd26a3e10f66318e9ff8b588be9d57367c9561989", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7a5/7a57ed30bfb5fece3eba93944d218186253c4c4dbdd8dc64a7167265a69fe2b6.mp3", "archive_relative_path": "raw/audio/7a5/7a57ed30bfb5fece3eba93944d218186253c4c4dbdd8dc64a7167265a69fe2b6.mp3" } ] } ], "prediction": "Wela'gwe'g etlmi'g'p We'gwi'g.", "reference": "Wela'gwe'g pewi'g'p gaqtugwewe'sm." }, { "id": "mic-sent-bdc22b90ae5e74a038b071b9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has accidently burned his/her hand while playing with fire.", "output_text": "Gis pejoqs'g ugtpitn ge's maligo'tg pugtew.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has accidently burned his/her hand while playing with fire.", "mic_Latn": "Gis pejoqs'g ugtpitn ge's maligo'tg pugtew." }, "canonical_ref": "entries/p/pejoqs'g/pejoqs'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-26673482e7e4850ad8db", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pejoqs'g/pejoqs'g.html", "entry_url": "https://mikmaqonline.org/entries/p/pejoqs'g/pejoqs'g.html", "headword": "pejoqs'g", "example_index": 0, "raw_html_path": "raw/entries/055e98c41939729fa042c679fa98141b9e58fd799650f4b0d008ea1aff22e938.html", "raw_html_sha256": "96684e9868e76d74940a1d5e993687497e2c833d5401af90e12fbd90d6d623a6", "fetched_at": "2026-07-12T02:43:26.083Z", "recordings": [ { "recording_id": "d7f93e1c937ff7b843e09bfc7e94065bdc7817dff7d844b34765d341a247076f", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1d4/1d466c348814c13a0b737c8cfeb63b8cb2f757b6bd8401ab0980b3652d10adab.mp3", "archive_relative_path": "raw/audio/1d4/1d466c348814c13a0b737c8cfeb63b8cb2f757b6bd8401ab0980b3652d10adab.mp3" } ] } ], "prediction": "Pugwelg'g ugta'latl ta'n tujiw gesatg.", "reference": "Gis pejoqs'g ugtpitn ge's maligo'tg pugtew." }, { "id": "mic-sent-bf612ca6cea29d1bdf015ed1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Peter stamps out the fire before going to sleep.", "output_text": "Ge's mu' nepagw Pie'l naqasuetesg'g pugtew.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Peter stamps out the fire before going to sleep.", "mic_Latn": "Ge's mu' nepagw Pie'l naqasuetesg'g pugtew." }, "canonical_ref": "entries/n/naqasuetesg'g/naqasuetesg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-35f517e8556f47d995aa", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/naqasuetesg'g/naqasuetesg'g.html", "entry_url": "https://mikmaqonline.org/entries/n/naqasuetesg'g/naqasuetesg'g.html", "headword": "naqasuetesg'g", "example_index": 0, "raw_html_path": "raw/entries/a4d8c42bcee8b79b4e1a459aabbf8c6d274fc7640c2c1898c4d9c3461d776a0b.html", "raw_html_sha256": "d4ee6be22dd87972750049bbb14ef0d9cc9c2c07cf4a105a7f9f48f490d66669", "fetched_at": "2026-07-12T02:42:03.734Z", "recordings": [ { "recording_id": "763394fddd314b28d1da4300453542586d5a0cc8e2f9b155dbb54e9f78f6c4d0", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4c7/4c732c38433d8c2e7f5b960fb86b3375261a062618d782f7bbb6b608ae940057.mp3", "archive_relative_path": "raw/audio/4c7/4c732c38433d8c2e7f5b960fb86b3375261a062618d782f7bbb6b608ae940057.mp3" } ] } ], "prediction": "Pie'l gesatg ugjit gesgmnaq ugjit.", "reference": "Ge's mu' nepagw Pie'l naqasuetesg'g pugtew." }, { "id": "mic-sent-bf6e84831aba395e9278de74:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little animals are going along, following their mother.", "output_text": "Wi'sitji'jg pemita'jig, pemulgwala'titl uggwijual.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little animals are going along, following their mother.", "mic_Latn": "Wi'sitji'jg pemita'jig, pemulgwala'titl uggwijual." }, "canonical_ref": "entries/w/wi'sisji'j/wi'sisji'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-069de50723fe5ade2513", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wi'sisji'j/wi'sisji'j.html", "entry_url": "https://mikmaqonline.org/entries/w/wi'sisji'j/wi'sisji'j.html", "headword": "wi'sisji'j", "example_index": 0, "raw_html_path": "raw/entries/8dbea78b8813b1e1b8441b2cb75f9b84416098b3bad4a9afd32058f8fd1cdffc.html", "raw_html_sha256": "3c184c1a6b7c67d6d8c4a589fc84e379c25ccc0d855eee814a9cb1e4e68a763d", "fetched_at": "2026-07-12T02:47:39.370Z", "recordings": [ { "recording_id": "b14cbdd7f298db3cfc405872715c4482940309194ef7045b3a5202f103bdab72", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/58c/58c0ee7466a969c8e2f3c905fc7cc76b844464bf26c9d5320172d75b4e5f046c.mp3", "archive_relative_path": "raw/audio/58c/58c0ee7466a969c8e2f3c905fc7cc76b844464bf26c9d5320172d75b4e5f046c.mp3" } ] } ], "prediction": "Lpa'tuji'ji'j na'te'jig, gesatg ugjig.", "reference": "Wi'sitji'jg pemita'jig, pemulgwala'titl uggwijual." }, { "id": "mic-sent-bf8cb46a0c541c547c19eb5e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It has been a long time since I've seen a partridge anywhere.", "output_text": "Gis sa'q giaspnnmi'g plawej tami.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It has been a long time since I've seen a partridge anywhere.", "mic_Latn": "Gis sa'q giaspnnmi'g plawej tami." }, "canonical_ref": "entries/p/plawej/plawej.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-896c8b437843e2d5ab49", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/plawej/plawej.html", "entry_url": "https://mikmaqonline.org/entries/p/plawej/plawej.html", "headword": "plawej", "example_index": 0, "raw_html_path": "raw/entries/2497dd0f0eb1679e85184e048f310e92f78d0954c4c7650db4ec0ebd9dcbf786.html", "raw_html_sha256": "6e483aa866924ed86d97541af2d091a8ab27406613723395e0690adedc0f0efc", "fetched_at": "2026-07-12T02:44:12.006Z", "recordings": [ { "recording_id": "73a0ae62b701a9636870b70ebf662434b56b6034475f3a3db62df3c82de5a340", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/77f/77ff2b25091cef21517bb461436c22a304ed9fae9b166578284a8b7122e60c9e.mp3", "archive_relative_path": "raw/audio/77f/77ff2b25091cef21517bb461436c22a304ed9fae9b166578284a8b7122e60c9e.mp3" } ] } ], "prediction": "Gi's gi's nige' nemi'g na gmu'ji'j ta'n tujiw.", "reference": "Gis sa'q giaspnnmi'g plawej tami." }, { "id": "mic-sent-bf992e63e9c8b09771a8227d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This world is crazy.", "output_text": "Elue'wiaq na ula ugs'tqamu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This world is crazy.", "mic_Latn": "Elue'wiaq na ula ugs'tqamu." }, "canonical_ref": "entries/e/elue'wiaq/elue'wiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2968a49da8a6032a47ac", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elue'wiaq/elue'wiaq.html", "entry_url": "https://mikmaqonline.org/entries/e/elue'wiaq/elue'wiaq.html", "headword": "elue'wiaq", "example_index": 0, "raw_html_path": "raw/entries/225cf7f1b2c0067a68f8e82b4ad00cfc733f517a66bc11db6df1da974bd42d00.html", "raw_html_sha256": "e8c6230ffa9a1fbd085d9e0fa724a4060226aa36cdfba206ea073c455f381f83", "fetched_at": "2026-07-12T02:37:54.251Z", "recordings": [ { "recording_id": "42f207e94044764d263f21325caf7db4284ac562cb2c81b2098ebd3979f15508", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8c6/8c67aa7a37b75b80f2d2e9bacbfa135d92fee242df4a1b6f240a39935dd2e75a.mp3", "archive_relative_path": "raw/audio/8c6/8c67aa7a37b75b80f2d2e9bacbfa135d92fee242df4a1b6f240a39935dd2e75a.mp3" } ] } ], "prediction": "We'gwi'g na ula gmu'j.", "reference": "Elue'wiaq na ula ugs'tqamu." }, { "id": "mic-sent-c11d1c97e0e4cad71a0d53c7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Let's cook (for ourselves) some peas.", "output_text": "Alawe'l wisugwanej.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Let's cook (for ourselves) some peas.", "mic_Latn": "Alawe'l wisugwanej." }, "canonical_ref": "entries/a/alawei/alawei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3d2c741a949372ea712c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/alawei/alawei.html", "entry_url": "https://mikmaqonline.org/entries/a/alawei/alawei.html", "headword": "alawei", "example_index": 0, "raw_html_path": "raw/entries/c01e42d73d48ecdd7a8035e5245e7db59dfaceeb1c3e6ca16930b279ed780e10.html", "raw_html_sha256": "87ef1f3380263a3de92f071df58fe1b7635ddb0bf37baaeb8f617bae1360e116", "fetched_at": "2026-07-12T02:36:38.814Z", "recordings": [ { "recording_id": "2ccbf3d7167d43af74b7797f9bef52f9c5ee0ec5729383ec6170d6e07ed463ba", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/20d/20dcf68e6539fe5b04576f75c5593c8c85e911a77ce85f792e2fbf648f7db626.mp3", "archive_relative_path": "raw/audio/20d/20dcf68e6539fe5b04576f75c5593c8c85e911a77ce85f792e2fbf648f7db626.mp3" } ] } ], "prediction": "Ge' lugowa'sij gmu'ji'j.", "reference": "Alawe'l wisugwanej." }, { "id": "mic-sent-c120fef0173124efad533848:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The painter must thin his/her paint before he/she uses it.", "output_text": "Nujimilamugwa'teget amujpa pepga'latl ugpent'ml gesgmnaq e'wagw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The painter must thin his/her paint before he/she uses it.", "mic_Latn": "Nujimilamugwa'teget amujpa pepga'latl ugpent'ml gesgmnaq e'wagw." }, "canonical_ref": "entries/p/pepga'latl/pepga'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-16ed7f57c6e7a10429b9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pepga'latl/pepga'latl.html", "entry_url": "https://mikmaqonline.org/entries/p/pepga'latl/pepga'latl.html", "headword": "pepga'latl", "example_index": 0, "raw_html_path": "raw/entries/3828e41147dbf959fe9445d0e94b01a52d561f17c1bbdf00141266500edaa3bb.html", "raw_html_sha256": "1e9020daf5abf24f3add03dc1373a59bc2b4ced3fcbc4e79b9f86e9b3d83dd54", "fetched_at": "2026-07-12T02:43:38.948Z", "recordings": [ { "recording_id": "a54219d5d81f444d19ced42629c4837fcdb37d4695bc5033f462921ec62b5af6", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ed8/ed8a41474b5695d9fc9e3472ef48fed57e14432cd80ce832921059213aea7f86.mp3", "archive_relative_path": "raw/audio/ed8/ed8a41474b5695d9fc9e3472ef48fed57e14432cd80ce832921059213aea7f86.mp3" } ] } ], "prediction": "Amujpa'toqann amujpa gmu'j ugjit gesgmnaq ugjit.", "reference": "Nujimilamugwa'teget amujpa pepga'latl ugpent'ml gesgmnaq e'wagw." }, { "id": "mic-sent-c13a9282ce288f289024cecc:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There are many kinds of stores in the city.", "output_text": "Magasann milamu'gl gjigang.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There are many kinds of stores in the city.", "mic_Latn": "Magasann milamu'gl gjigang." }, "canonical_ref": "entries/m/magasan/magasan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5c0a817589096595e36d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/magasan/magasan.html", "entry_url": "https://mikmaqonline.org/entries/m/magasan/magasan.html", "headword": "magasan", "example_index": 0, "raw_html_path": "raw/entries/ae71c305608c56ee2a21506773ebdf560351bf06d4f4ad3e24334da677a4fb46.html", "raw_html_sha256": "619cdeec2b40cc23a157c55eee126a5592e8363e8eab35e39a4a19f7872239b3", "fetched_at": "2026-07-12T02:40:41.325Z", "recordings": [ { "recording_id": "6f0f3fb8ca8f7a74b49c7aaa91df8e4f0327ee1f27aa67356f4fdab69b100a0c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/273/273283d8076d620e883e19aba13970081383b17456a2704f27f8cec27a81ff5d.mp3", "archive_relative_path": "raw/audio/273/273283d8076d620e883e19aba13970081383b17456a2704f27f8cec27a81ff5d.mp3" } ] } ], "prediction": "Pugwelg'g na mawtigwi'jig negm.", "reference": "Magasann milamu'gl gjigang." }, { "id": "mic-sent-c185c607a2d7ace551c3eb2d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The one that's going out slams the door.", "output_text": "Iltijieget ga'qan ala pemtu'et.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The one that's going out slams the door.", "mic_Latn": "Iltijieget ga'qan ala pemtu'et." }, "canonical_ref": "entries/i/iltijieget/iltijieget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c75e2ac6abcb945f540f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/iltijieget/iltijieget.html", "entry_url": "https://mikmaqonline.org/entries/i/iltijieget/iltijieget.html", "headword": "iltijieget", "example_index": 0, "raw_html_path": "raw/entries/016c944869e646f99fc0254283e8ce5e9b7e8590ad7c8f9905e36cefb5469530.html", "raw_html_sha256": "97776c61dd29039eff0db054ad34fdfc947ed82d69e3b9ee4ea2d7c9f0d8be42", "fetched_at": "2026-07-12T02:40:11.192Z", "recordings": [ { "recording_id": "63054121a36c441cf6ad8d10a87402b0154ab40343f99982b303c243bce29df2", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/25d/25d38eec746a3bb4f981eb7a9d921e230cb3483c78dcf6faca24274223dc52bf.mp3", "archive_relative_path": "raw/audio/25d/25d38eec746a3bb4f981eb7a9d921e230cb3483c78dcf6faca24274223dc52bf.mp3" } ] } ], "prediction": "E's'g e'pite'g ugjit ga'qan.", "reference": "Iltijieget ga'qan ala pemtu'et." }, { "id": "mic-sent-c1ce74dc287777012fbb067f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "His/she is the slowest one of all.", "output_text": "Ula negm na maw pawa'sit", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "His/she is the slowest one of all.", "mic_Latn": "Ula negm na maw pawa'sit" }, "canonical_ref": "entries/p/pawa'sit/pawa'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e9de36d20c05fa7ee865", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pawa'sit/pawa'sit.html", "entry_url": "https://mikmaqonline.org/entries/p/pawa'sit/pawa'sit.html", "headword": "pawa'sit", "example_index": 0, "raw_html_path": "raw/entries/cc27cd705f8068e4f27d0816fdebe819218d3695579f7ba8f3d9a056fa356163.html", "raw_html_sha256": "1e7e18e46a613f3987c7c15bcb43454190d83422b21ce2a579a98bc78025047b", "fetched_at": "2026-07-12T02:43:19.148Z", "recordings": [ { "recording_id": "5d824e3d6f6b3e10ef88b71ec0905bfe259c24bc52a533b7728710c5e4286a21", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/bb5/bb5365e597aedfd589b7850b50e44b48969adac6eec685d120421550ee254930.mp3", "archive_relative_path": "raw/audio/bb5/bb5365e597aedfd589b7850b50e44b48969adac6eec685d120421550ee254930.mp3" } ] } ], "prediction": "Lpa wi'gwi'g ta'n te'sijig.", "reference": "Ula negm na maw pawa'sit" }, { "id": "mic-sent-c2489f6df4ee68c8629df7da:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The young girl squeezes her doll into the bag and leaves.", "output_text": "E'pite'ji'j pijigwalatl ugtapsute'gann muntigtug aq maja'sit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The young girl squeezes her doll into the bag and leaves.", "mic_Latn": "E'pite'ji'j pijigwalatl ugtapsute'gann muntigtug aq maja'sit." }, "canonical_ref": "entries/p/pijigwalatl/pijigwalatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-58e9aa58f2996d20f4e4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pijigwalatl/pijigwalatl.html", "entry_url": "https://mikmaqonline.org/entries/p/pijigwalatl/pijigwalatl.html", "headword": "pijigwalatl", "example_index": 0, "raw_html_path": "raw/entries/b35dd7958468297cec4f094b38c62a20889aa479bc4846a11399f65b0df4be89.html", "raw_html_sha256": "2777e498d9bc7c279d62cde81886e80d03146cdf1c35a7845211d262eb0400c1", "fetched_at": "2026-07-12T02:43:55.939Z", "recordings": [ { "recording_id": "5b7bbdf993c6badc3ea0cd297ad20a006a7511e3afb58a6dd96889698528e23a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3c3/3c33af7b8a88e1a3e69db3d0059aff7f0d1349819794d5b674f2c38a3e651894.mp3", "archive_relative_path": "raw/audio/3c3/3c33af7b8a88e1a3e69db3d0059aff7f0d1349819794d5b674f2c38a3e651894.mp3" } ] } ], "prediction": "E'pite'ji'j gesatgmatl ugta'latl ugjitl aq wejiaq.", "reference": "E'pite'ji'j pijigwalatl ugtapsute'gann muntigtug aq maja'sit." }, { "id": "mic-sent-c326876951be0239bf7d6d56:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Sometimes a person heals very quickly.", "output_text": "Jijuaqa wen mawnaqsinijgit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Sometimes a person heals very quickly.", "mic_Latn": "Jijuaqa wen mawnaqsinijgit." }, "canonical_ref": "entries/n/naqsinijgit/naqsinijgit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ae0e039cf9c2fa956efb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/naqsinijgit/naqsinijgit.html", "entry_url": "https://mikmaqonline.org/entries/n/naqsinijgit/naqsinijgit.html", "headword": "naqsinijgit", "example_index": 0, "raw_html_path": "raw/entries/f74c00f172fe6f122d24b0509d104f813963a4157355dfdfc7104b049fbb18e2.html", "raw_html_sha256": "19d6edb05965179a388a0713d01db9a49669e9b2411795c36fac78632eaecee3", "fetched_at": "2026-07-12T02:42:04.639Z", "recordings": [ { "recording_id": "fac8acdaac9281ad103d09dffe7ea772d04ca6f717148056c50cce5695f9ada2", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/01c/01c24d8ce6697739811c2391da1660d4f36d12a4e8be770aa384ff9266eb31ae.mp3", "archive_relative_path": "raw/audio/01c/01c24d8ce6697739811c2391da1660d4f36d12a4e8be770aa384ff9266eb31ae.mp3" } ] } ], "prediction": "We'gwi'g na ms't goqwei'g.", "reference": "Jijuaqa wen mawnaqsinijgit." }, { "id": "mic-sent-c36332e903d4a9275b7febfb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Here where we live, we have to heat our homes well in the wiinter time.", "output_text": "Gesig ula wigulti'gw, amujpa welp'sma'tigw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Here where we live, we have to heat our homes well in the wiinter time.", "mic_Latn": "Gesig ula wigulti'gw, amujpa welp'sma'tigw." }, "canonical_ref": "entries/w/welp'smat/welp'smat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8d4530d3030c985cf15a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/welp'smat/welp'smat.html", "entry_url": "https://mikmaqonline.org/entries/w/welp'smat/welp'smat.html", "headword": "welp'smat", "example_index": 0, "raw_html_path": "raw/entries/9eba936682a8d0a2974ea89819464ef57627cd7bd6f3649f0ecf30e486a7ea18.html", "raw_html_sha256": "faa343cf5f77c3cb422377842060071fc000b5eb15ab83b687ff231bc7b97255", "fetched_at": "2026-07-12T02:47:08.201Z", "recordings": [ { "recording_id": "53456fdc9543309de9a0f5f456d2bfb420dbc41812492ac0494aad6e13d615a5", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2bd/2bd885f5b191adafc2c0c132290a83b9a6948aca6bc20e94f2369a3bf43f233c.mp3", "archive_relative_path": "raw/audio/2bd/2bd885f5b191adafc2c0c132290a83b9a6948aca6bc20e94f2369a3bf43f233c.mp3" } ] } ], "prediction": "Ula we'gwi'g, amujpa gmu'ji'jig amgwesg'p'tijig.", "reference": "Gesig ula wigulti'gw, amujpa welp'sma'tigw." }, { "id": "mic-sent-c4ec1e70c692a1866cb9ff1e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "An infant will start to suck as soon as a bottle is put to it's mouth.", "output_text": "Smtug qopisun nunat ta'n tujiw pu'tail ugtung pitasga'tuj.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "An infant will start to suck as soon as a bottle is put to it's mouth.", "mic_Latn": "Smtug qopisun nunat ta'n tujiw pu'tail ugtung pitasga'tuj." }, "canonical_ref": "entries/n/nunat/nunat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5d79e8e424039bb0ef80", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nunat/nunat.html", "entry_url": "https://mikmaqonline.org/entries/n/nunat/nunat.html", "headword": "nunat", "example_index": 0, "raw_html_path": "raw/entries/aad2910bb94c1f01171994d6a6382fd5c091440fe9a088f69b139111526b31f8.html", "raw_html_sha256": "80d5f51e06cbba830400c7c05e3cbbb0176dea51a9a454dbf1703ab9fca7eda0", "fetched_at": "2026-07-12T02:42:52.999Z", "recordings": [ { "recording_id": "72fd0ff7a7cbc000cd0598ef36fa5496774eb6d79f46eb8de0bdcabcc4066c1a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5f0/5f036976d4678f6c0265b63efeb2309e2b020ad89a562f68cbc8af0477600a8b.mp3", "archive_relative_path": "raw/audio/5f0/5f036976d4678f6c0265b63efeb2309e2b020ad89a562f68cbc8af0477600a8b.mp3" } ] } ], "prediction": "Lpa'tu'ji'j poqji'jit ta'n tujiw pas'g e'pite'l.", "reference": "Smtug qopisun nunat ta'n tujiw pu'tail ugtung pitasga'tuj." }, { "id": "mic-sent-c4fcd5ec8baa7a6c0504632b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The boy has clean nostrils but he still has a severe cold.", "output_text": "Waqamitnat lpa'tuj gatu me' tewjitgeia'tat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The boy has clean nostrils but he still has a severe cold.", "mic_Latn": "Waqamitnat lpa'tuj gatu me' tewjitgeia'tat." }, "canonical_ref": "entries/w/waqamitnat/waqamitnat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d321cad43a840bc9cfaf", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waqamitnat/waqamitnat.html", "entry_url": "https://mikmaqonline.org/entries/w/waqamitnat/waqamitnat.html", "headword": "waqamitnat", "example_index": 0, "raw_html_path": "raw/entries/7c164e2f1be5dc9034e44330c79c39ac54f025d11ba0613c2b59939fe75aee9b.html", "raw_html_sha256": "a50949f5fd4e0a96798c4b19ea0223ad4943f290ea4d88be2245e34bb48e4a3e", "fetched_at": "2026-07-12T02:46:38.737Z", "recordings": [ { "recording_id": "c8217e0aa6644845586d18e543b5f913e3e9c1c5df6b491e8aeca2bd33ac257c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/455/455c674eb2465b7eb97649aeb6856901965b2bfa468de009545848ead98c66f6.mp3", "archive_relative_path": "raw/audio/455/455c674eb2465b7eb97649aeb6856901965b2bfa468de009545848ead98c66f6.mp3" } ] } ], "prediction": "Lpa'tu'ji'j gesatg, gatu gi's gaqama'sit.", "reference": "Waqamitnat lpa'tuj gatu me' tewjitgeia'tat." }, { "id": "mic-sent-c518dac653168c1788be888b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Are you ill? Your face is so wan.", "output_text": "Gesnugwan? Teliewlapewin.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Are you ill? Your face is so wan.", "mic_Latn": "Gesnugwan? Teliewlapewin." }, "canonical_ref": "entries/g/gesnugwat/gesnugwat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-66df83853bc7a4abc36c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesnugwat/gesnugwat.html", "entry_url": "https://mikmaqonline.org/entries/g/gesnugwat/gesnugwat.html", "headword": "gesnugwat", "example_index": 0, "raw_html_path": "raw/entries/154815377a4414bf513e62787a424e15063011f27e67d206d4e07317d9397a69.html", "raw_html_sha256": "8664633d1c9cfbbeec3789fc8900f319447c765611730d2d47be7300cb5e9e94", "fetched_at": "2026-07-12T02:39:17.271Z", "recordings": [ { "recording_id": "943727e9c09a49a922255c84136da03e04a53f95a4d2ac902984a9d297dbbfad", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/882/8822583d3cd6d460bc3ce6f437fe8c906856a564a1d2510e3bd0d10907cae117.mp3", "archive_relative_path": "raw/audio/882/8822583d3cd6d460bc3ce6f437fe8c906856a564a1d2510e3bd0d10907cae117.mp3" } ] } ], "prediction": "Ge's'g? Tetuji'j na gmu'j.", "reference": "Gesnugwan? Teliewlapewin." }, { "id": "mic-sent-c568343082ea0c202178c281:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My hands are tired.", "output_text": "Npitnn gispnegl", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My hands are tired.", "mic_Latn": "Npitnn gispnegl" }, "canonical_ref": "entries/g/gispneg/gispneg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-52091369d3774ac8cb86", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gispneg/gispneg.html", "entry_url": "https://mikmaqonline.org/entries/g/gispneg/gispneg.html", "headword": "gispneg", "example_index": 0, "raw_html_path": "raw/entries/0c2bded58355c024ffa5b05188f3326375991cee84249f426a8d3845e82924e6.html", "raw_html_sha256": "8d3cce2c6d676019bac84b7b9aef95c111571f00569c02f0ffe8bfca5d7449ed", "fetched_at": "2026-07-12T02:39:42.491Z", "recordings": [ { "recording_id": "70bf98cb1cf9670e57c6c171eea872d053b96248926999c79d24b2bde50784fb", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6a3/6a330d8f198ae0a83732bd4eeaf116d74a97b0c3e90faad7bfbeee1ab2ede524.mp3", "archive_relative_path": "raw/audio/6a3/6a330d8f198ae0a83732bd4eeaf116d74a97b0c3e90faad7bfbeee1ab2ede524.mp3" } ] } ], "prediction": "Pugwelg na mawti'g.", "reference": "Npitnn gispnegl" }, { "id": "mic-sent-c5c9424e93269055a3c74d00:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where is the top of the head?", "output_text": "Tami eteg ge'gwatpan?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where is the top of the head?", "mic_Latn": "Tami eteg ge'gwatpan?" }, "canonical_ref": "entries/g/ge'gwatpan/ge'gwatpan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f3ecd4276d17bc1f785e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/ge'gwatpan/ge'gwatpan.html", "entry_url": "https://mikmaqonline.org/entries/g/ge'gwatpan/ge'gwatpan.html", "headword": "ge'gwatpan", "example_index": 0, "raw_html_path": "raw/entries/3b675d70247fb461f260b8b6c7dd5e807e5e9d337814965501e86bdc22e9359e.html", "raw_html_sha256": "c9685b9a99e0ac6fff6a98f5e8de90867978d4cf8e75c6240b05e1b28274ffa1", "fetched_at": "2026-07-12T02:38:52.758Z", "recordings": [ { "recording_id": "1a7508ccfdc7883d204605973eea5de3b0235074546530c08d14a6c4bca047b5", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6a2/6a281d3ee2018f2a6dff8a6a94608ff95979c78070812e0611f2c4df4bb83969.mp3", "archive_relative_path": "raw/audio/6a2/6a281d3ee2018f2a6dff8a6a94608ff95979c78070812e0611f2c4df4bb83969.mp3" } ] } ], "prediction": "Tami we'gwi'g ta'n tujiw?", "reference": "Tami eteg ge'gwatpan?" }, { "id": "mic-sent-c5f9903351d2132c7c3f7705:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she will have to lighten his/her boat if he/she doesn't want to get stuck on shore.", "output_text": "Amuj pana ne'naqpega'tew ugtul mu 'gtu'niwetesinug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she will have to lighten his/her boat if he/she doesn't want to get stuck on shore.", "mic_Latn": "Amuj pana ne'naqpega'tew ugtul mu 'gtu'niwetesinug." }, "canonical_ref": "entries/n/ne'naqpega'toq/ne'naqpega'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-51610be059568d1f56fa", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ne'naqpega'toq/ne'naqpega'toq.html", "entry_url": "https://mikmaqonline.org/entries/n/ne'naqpega'toq/ne'naqpega'toq.html", "headword": "ne'naqpega'toq", "example_index": 0, "raw_html_path": "raw/entries/0279d8637fb359d3e7c2c951840f5e1451cc21e3111ea8666f0af6361d52ff64.html", "raw_html_sha256": "2a3423522b56c5bc3228b9b567b20fbc9d8f7e6f6bf8494c17f636a2bec14fba", "fetched_at": "2026-07-12T02:36:08.609Z", "recordings": [ { "recording_id": "fc18809a5a48bbf473d8ceb092e627abd745a344583953fe59f67a38701be2ac", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/06a/06a1e828bc255be3fd46909020e540eff2c9d1f33690719076589bfba35529a5.mp3", "archive_relative_path": "raw/audio/06a/06a1e828bc255be3fd46909020e540eff2c9d1f33690719076589bfba35529a5.mp3" } ] } ], "prediction": "Amujpa amujpa'latl ugtatl ugjitl ma' tujiw nmu'j.", "reference": "Amuj pana ne'naqpega'tew ugtul mu 'gtu'niwetesinug." }, { "id": "mic-sent-c6570c9fbff2ab571f21744e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Our companion at this time (finally) looks tired.", "output_text": "Gispnapewit nugu' gigmenu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Our companion at this time (finally) looks tired.", "mic_Latn": "Gispnapewit nugu' gigmenu." }, "canonical_ref": "entries/g/gispnapewit/gispnapewit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-22b502e90ca0c2bf9398", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gispnapewit/gispnapewit.html", "entry_url": "https://mikmaqonline.org/entries/g/gispnapewit/gispnapewit.html", "headword": "gispnapewit", "example_index": 0, "raw_html_path": "raw/entries/39948a6ceff51e68ab90cd8b4578cf569aa625f765545cc91de1ffc887c282a3.html", "raw_html_sha256": "9e9ec68d3da76cf99656193754586a14298eb6f6df6ef1370a685d30fec0d337", "fetched_at": "2026-07-12T02:39:42.383Z", "recordings": [ { "recording_id": "9284f0c18e64d71b6264f58642877f06055069f0cb8a3692bbc81ed5f3edf322", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/268/26838f462142be6e9526f65013f76e9f302b4e3bae9514afe35fe72ba3787031.mp3", "archive_relative_path": "raw/audio/268/26838f462142be6e9526f65013f76e9f302b4e3bae9514afe35fe72ba3787031.mp3" } ] } ], "prediction": "Wela's'g na ula nige' gisgugwet.", "reference": "Gispnapewit nugu' gigmenu." }, { "id": "mic-sent-c6604e37dec6cbf7cab46f53:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "We will eat hot soup for lunch.", "output_text": "Malqutesnu epteg lasup ugjit mewlia'gowei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "We will eat hot soup for lunch.", "mic_Latn": "Malqutesnu epteg lasup ugjit mewlia'gowei." }, "canonical_ref": "entries/e/epteg/epteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-78d25be1e047dad42ed2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/epteg/epteg.html", "entry_url": "https://mikmaqonline.org/entries/e/epteg/epteg.html", "headword": "epteg", "example_index": 0, "raw_html_path": "raw/entries/a8b4119f18dd7e0af9f8c4a6238ed421b7a510c5037ec390a401e8048b2aea74.html", "raw_html_sha256": "dbd7fcad1dc4e3ef2f5bc24229684354fb6be974965be4ad419e5b1f111ba60a", "fetched_at": "2026-07-12T02:38:11.832Z", "recordings": [ { "recording_id": "872841c18cef45c774aa462ece3537f8a928869f3a25d8208faab0f0da09325c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/60a/60a46bb7c3772b48f3ae816b435612161b1415f02553ca71d0b53313c0715619.mp3", "archive_relative_path": "raw/audio/60a/60a46bb7c3772b48f3ae816b435612161b1415f02553ca71d0b53313c0715619.mp3" } ] } ], "prediction": "Wela's'g na wesapsu'g wesgowaqan.", "reference": "Malqutesnu epteg lasup ugjit mewlia'gowei." }, { "id": "mic-sent-c6852b48fee1ccdf1cf808ad:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I'm almost sixty years old.", "output_text": "Geget as'gom te'sisgegipuna'i.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I'm almost sixty years old.", "mic_Latn": "Geget as'gom te'sisgegipuna'i." }, "canonical_ref": "entries/g/geget/geget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7c779512b1fd70c50a4b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/geget/geget.html", "entry_url": "https://mikmaqonline.org/entries/g/geget/geget.html", "headword": "geget", "example_index": 0, "raw_html_path": "raw/entries/e9729329d285372d65fb9f6906853b48bdd15bc10bf299464b782e9194d93502.html", "raw_html_sha256": "ee2dd9683e81f9ba4c3d51f7797100a4a4f06f6d771fce87456533699a67c7e3", "fetched_at": "2026-07-12T02:38:47.825Z", "recordings": [ { "recording_id": "42d9267fa04251d22369a6594d7afa1a870873e691f8638ec8fd901b1e745a11", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d07/d07372f8a2f922a6a35b399f561904c7c8471b1417d40d21ac0dcbe8cf8d4e89.mp3", "archive_relative_path": "raw/audio/d07/d07372f8a2f922a6a35b399f561904c7c8471b1417d40d21ac0dcbe8cf8d4e89.mp3" } ] } ], "prediction": "Gi's te'sijig ta'n tujiw te's'g.", "reference": "Geget as'gom te'sisgegipuna'i." }, { "id": "mic-sent-c6bff96e03f757e7edb1a2db:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What time is the tide.", "output_text": "Tale'tew jigwapa'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What time is the tide.", "mic_Latn": "Tale'tew jigwapa'n." }, "canonical_ref": "entries/j/jigwapa'n/jigwapa'n.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-905258b4c30fc80d96cc", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jigwapa'n/jigwapa'n.html", "entry_url": "https://mikmaqonline.org/entries/j/jigwapa'n/jigwapa'n.html", "headword": "jigwapa'n", "example_index": 0, "raw_html_path": "raw/entries/a515b2d9b27b65264d234eb9e08b8b2926bfaafb0a5930cdb462c94d7edade50.html", "raw_html_sha256": "46330789e1602b5915b1a04909fe25957fb4b60667fcf95cff9e48d860ec7094", "fetched_at": "2026-07-12T02:40:19.520Z", "recordings": [ { "recording_id": "76946a73f6f14109b81bc703764381a20d8e89fb6056c7e5864797bcb9da45f8", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/238/238e671121c9db490f7e9761f15934e6a57d490c8fbfdb3051f27c940dee5d30.mp3", "archive_relative_path": "raw/audio/238/238e671121c9db490f7e9761f15934e6a57d490c8fbfdb3051f27c940dee5d30.mp3" } ] } ], "prediction": "Ta's'g ta'n te'sipow.", "reference": "Tale'tew jigwapa'n." }, { "id": "mic-sent-c79022ceb0a0414eda9222c4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Tom appreciates when his possessions are well taken by others.", "output_text": "Tuma na mawigsatg welo'tmugsij utapsum.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Tom appreciates when his possessions are well taken by others.", "mic_Latn": "Tuma na mawigsatg welo'tmugsij utapsum." }, "canonical_ref": "entries/w/welo'tmugsit/welo'tmugsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a8517d70148d4c366976", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/welo'tmugsit/welo'tmugsit.html", "entry_url": "https://mikmaqonline.org/entries/w/welo'tmugsit/welo'tmugsit.html", "headword": "welo'tmugsit", "example_index": 0, "raw_html_path": "raw/entries/b0c6d9a25ab4ab7e5dd182ddf3bc056ca87ab1985998bb5502cb2cb1444af1e1.html", "raw_html_sha256": "df8fd3a72082056706296c0d6f0b33ac5dcad77ef7c763d4363bbf7de8d24a80", "fetched_at": "2026-07-12T02:47:07.112Z", "recordings": [ { "recording_id": "01978737afa8a9ce515c666f7ba67f050a41e9488db2cfc1b0ae96f6c0cbe8c2", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1dc/1dc6b633efc9793012d3a5fbdbdd6efe972abc59c8cfcafc007509352cf20d65.mp3", "archive_relative_path": "raw/audio/1dc/1dc6b633efc9793012d3a5fbdbdd6efe972abc59c8cfcafc007509352cf20d65.mp3" } ] } ], "prediction": "Tuma gesatg ta'n tujiw we'gwi'jg.", "reference": "Tuma na mawigsatg welo'tmugsij utapsum." }, { "id": "mic-sent-c7a4bc85b9d9d75526f8140d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It seems we've run out of milk.", "output_text": "Lne's mlagejg gaqanmaigwi'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It seems we've run out of milk.", "mic_Latn": "Lne's mlagejg gaqanmaigwi'g." }, "canonical_ref": "entries/l/lne's/lne's.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c8fe5cfab112ee171c19", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lne's/lne's.html", "entry_url": "https://mikmaqonline.org/entries/l/lne's/lne's.html", "headword": "lne's", "example_index": 0, "raw_html_path": "raw/entries/555d18f675e406edd02e9c276ce18cad7e254770dd0abf29067c6a5f35a8eff1.html", "raw_html_sha256": "68dd34a78d8aa43426bda0954d06e389f53cbf4460e8e0cba726e454bfa81a69", "fetched_at": "2026-07-12T02:40:36.202Z", "recordings": [ { "recording_id": "1be9500dd910143825441c1d5e8e4db6522f8d38d9770f397b5d57d49608c7fe", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/662/66241a2eb48e3d5c638e4914222bbdf6667a61ea1ca4feab422b6bc45ca5b5d3.mp3", "archive_relative_path": "raw/audio/662/66241a2eb48e3d5c638e4914222bbdf6667a61ea1ca4feab422b6bc45ca5b5d3.mp3" } ] } ], "prediction": "Telte's'g nuji'guoml mlagej.", "reference": "Lne's mlagejg gaqanmaigwi'g." }, { "id": "mic-sent-c7a612ca58d4dd2ecdb08e4c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend is headed this way and he/she is carrying some food.", "output_text": "Nitap wejgu'et aq pemapilg mijipjewei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend is headed this way and he/she is carrying some food.", "mic_Latn": "Nitap wejgu'et aq pemapilg mijipjewei." }, "canonical_ref": "entries/p/pemapilg/pemapilg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c52255965ebab43e7cb9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemapilg/pemapilg.html", "entry_url": "https://mikmaqonline.org/entries/p/pemapilg/pemapilg.html", "headword": "pemapilg", "example_index": 0, "raw_html_path": "raw/entries/dfe6ea73f82450f6b004cb522e462498ab651c3ed5e9b37055a1938ba8ec2433.html", "raw_html_sha256": "c1957b4bafa54640f72a90b01d6b70673f836e3dcaa1ccd7e215628cbb42815a", "fetched_at": "2026-07-12T02:43:29.596Z", "recordings": [ { "recording_id": "da8865737e40eb2d8d9015e8d8a88faa2ed4d317dcec8ec31ff9b86c94257486", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/690/69000b3a12df090b27a15cd0758d54d3538c789c32a35cefb786e1397b437310.mp3", "archive_relative_path": "raw/audio/690/69000b3a12df090b27a15cd0758d54d3538c789c32a35cefb786e1397b437310.mp3" } ] } ], "prediction": "Ula nitap etlpugwet aq gesatg ugjit.", "reference": "Nitap wejgu'et aq pemapilg mijipjewei." }, { "id": "mic-sent-c7dc4cc49caa225e76f3149c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When it's building its nest, the bird is at its busyist.", "output_text": "Ta'n tujiw etoq, na mawigtme'g sisip.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When it's building its nest, the bird is at its busyist.", "mic_Latn": "Ta'n tujiw etoq, na mawigtme'g sisip." }, "canonical_ref": "entries/e/etoq/etoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e71902a0f46f306d8e32", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/etoq/etoq.html", "entry_url": "https://mikmaqonline.org/entries/e/etoq/etoq.html", "headword": "etoq", "example_index": 0, "raw_html_path": "raw/entries/776a4269eb35045b6500f8a8ce396e5c03941af590ab17d092a089a800a9ef11.html", "raw_html_sha256": "e9574974e5448b529feff9c1858044ec6b3680d8f62003234a439809a0c9a051", "fetched_at": "2026-07-12T02:38:26.706Z", "recordings": [ { "recording_id": "d0306c52289d4cdfb85e4fce167d56e940d272cdaed784f8ef935dab322f7bfc", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/13b/13b9550f16c092ac230e6851da3f50c9c331348c7529d490e972fe5ec596d4f8.mp3", "archive_relative_path": "raw/audio/13b/13b9550f16c092ac230e6851da3f50c9c331348c7529d490e972fe5ec596d4f8.mp3" } ] } ], "prediction": "Ta'n tujiw ugjitl, lpa nmu'ji'j gisijig.", "reference": "Ta'n tujiw etoq, na mawigtme'g sisip." }, { "id": "mic-sent-c844ddcc2fbff340c3602100:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Those whose home has burned down must be provided for.", "output_text": "Wigwow gisnu'gwa'q, amujpa a'su'ngewujig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Those whose home has burned down must be provided for.", "mic_Latn": "Wigwow gisnu'gwa'q, amujpa a'su'ngewujig." }, "canonical_ref": "entries/a/a'su'ngewatl/a'su'ngewatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a2ed0fd46317c846c827", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/a'su'ngewatl/a'su'ngewatl.html", "entry_url": "https://mikmaqonline.org/entries/a/a'su'ngewatl/a'su'ngewatl.html", "headword": "a'su'ngewatl", "example_index": 0, "raw_html_path": "raw/entries/d4d0658013d7c13e634f80ca6c7c197aa024325065274e17d5ee9ceebb1852ab.html", "raw_html_sha256": "80d65d4d0c0a5330bc3e2f3907188da0135b620f0b109ec9b1fe3eecca4cbd4c", "fetched_at": "2026-07-12T02:37:23.138Z", "recordings": [ { "recording_id": "c6685b27565e5e67dc7beb880d89dbdbddc59196275bef1de8c2e5f6422a9718", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/454/45427515f6f17c5f6e0436b841b04fa9369e391cd97dcc2cf9cdc12e24671a3a.mp3", "archive_relative_path": "raw/audio/454/45427515f6f17c5f6e0436b841b04fa9369e391cd97dcc2cf9cdc12e24671a3a.mp3" } ] } ], "prediction": "Amujpa ta'n tujiw wenji'guomg amujpa'toq.", "reference": "Wigwow gisnu'gwa'q, amujpa a'su'ngewujig." }, { "id": "mic-sent-c84de382b7e89a3d8f7fa52f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "As I was rushing about, I almost tripped.", "output_text": "Ge'sg alnenaqa'si suel peji'taqamai.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "As I was rushing about, I almost tripped.", "mic_Latn": "Ge'sg alnenaqa'si suel peji'taqamai." }, "canonical_ref": "entries/p/peji'taqamat/peji'taqamat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d8f9be5784c98e4064dd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/peji'taqamat/peji'taqamat.html", "entry_url": "https://mikmaqonline.org/entries/p/peji'taqamat/peji'taqamat.html", "headword": "peji'taqamat", "example_index": 0, "raw_html_path": "raw/entries/4d0f799aa173ebd49a99da01e58eb696fe2940f29a97ab33f3ae5889fa2dcf1e.html", "raw_html_sha256": "68fd48df2040d75fadafb16abeb3d71bf5d79034e9029e9b19b6cc98a42c6693", "fetched_at": "2026-07-12T02:43:25.379Z", "recordings": [ { "recording_id": "9d24e0761fc844c9c09ab0268417622b52357b926b69a3de1e22c390112d40b4", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2b3/2b36c0efccf3fb706b441725d91be94d9aa1d02c14718a35240e8da335515b3b.mp3", "archive_relative_path": "raw/audio/2b3/2b36c0efccf3fb706b441725d91be94d9aa1d02c14718a35240e8da335515b3b.mp3" } ] } ], "prediction": "Ta'n tujiw gesatg, pas'g gesitpa's'g.", "reference": "Ge'sg alnenaqa'si suel peji'taqamai." }, { "id": "mic-sent-c8c4ddc2a29734fe525a33ae:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I know that Peter is a heavy smoker.", "output_text": "Pie'l geji'g negm wigumat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I know that Peter is a heavy smoker.", "mic_Latn": "Pie'l geji'g negm wigumat." }, "canonical_ref": "entries/w/wigumat/wigumat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-da96d5f490d8e32fe475", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wigumat/wigumat.html", "entry_url": "https://mikmaqonline.org/entries/w/wigumat/wigumat.html", "headword": "wigumat", "example_index": 0, "raw_html_path": "raw/entries/a52d4009bd03e2c404bd6006b4da994668a74d1f045cec85208ee0f47f98f4e7.html", "raw_html_sha256": "bdadd315f614c2f1001564e2e44e9eff739e3a3798098607ab1cae8b7d475742", "fetched_at": "2026-07-12T02:47:31.312Z", "recordings": [ { "recording_id": "b90e4cc900bf48040d9deda876d08e6d347e5972d8e3e4fea7bdfb358283e45e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4d3/4d35f649a186eddc6c730741936b4324e6d1b59890a31e7f1ac67b305e2b7b84.mp3", "archive_relative_path": "raw/audio/4d3/4d35f649a186eddc6c730741936b4324e6d1b59890a31e7f1ac67b305e2b7b84.mp3" } ] } ], "prediction": "Ge' gi'l gi's Pie'l na we'gwi'jig.", "reference": "Pie'l geji'g negm wigumat." }, { "id": "mic-sent-c918cc8bb736e6a8175538c1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The wire is coiled in the other room.", "output_text": "Qasawo'qapi el'tqeg a'se'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The wire is coiled in the other room.", "mic_Latn": "Qasawo'qapi el'tqeg a'se'g." }, "canonical_ref": "entries/e/el'tqeg/el'tqeg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a0de80232dd5f2655451", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/el'tqeg/el'tqeg.html", "entry_url": "https://mikmaqonline.org/entries/e/el'tqeg/el'tqeg.html", "headword": "el'tqeg", "example_index": 0, "raw_html_path": "raw/entries/486706aace43c92faa051d96b305709309346f9a44e924b21c470c5fb1d3f5a0.html", "raw_html_sha256": "0e1e3740353e9689178a37ca5516e3e2806f80e32ba960ae25bc470aaca839f9", "fetched_at": "2026-07-12T02:37:53.648Z", "recordings": [ { "recording_id": "d704ebba45d1a79e93032699076ba877252552e5685a324e3ef74c24bc309e4b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ae5/ae51b23471f676b48569d03c8eba0b4d9ffb71a31deb6f8377d59dcfdf4d1fd6.mp3", "archive_relative_path": "raw/audio/ae5/ae51b23471f676b48569d03c8eba0b4d9ffb71a31deb6f8377d59dcfdf4d1fd6.mp3" } ] } ], "prediction": "Pilei'g na wi'gwig ta'n tujiw wenji'guom.", "reference": "Qasawo'qapi el'tqeg a'se'g." }, { "id": "mic-sent-c95911505370d971fa2bbbd3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The hoop is part of the basket.", "output_text": "Loqwistaqan eliaq ligpenignigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The hoop is part of the basket.", "mic_Latn": "Loqwistaqan eliaq ligpenignigtug." }, "canonical_ref": "entries/l/loqwistaqan/loqwistaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-fcf1e4e898ac817bf609", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/loqwistaqan/loqwistaqan.html", "entry_url": "https://mikmaqonline.org/entries/l/loqwistaqan/loqwistaqan.html", "headword": "loqwistaqan", "example_index": 0, "raw_html_path": "raw/entries/f5771d247da5acd596bea8a0ae02bb9bcae1b328d50df7c4d0754f1aeaf18640.html", "raw_html_sha256": "91a9367bc5352d581a8eebb96a93deafb9417660014ba6072b1e19b0b8a43c90", "fetched_at": "2026-07-12T02:40:38.509Z", "recordings": [ { "recording_id": "87532abfcf4907a1c6cad5c6764b6e031dce553d0a266b7a56b780e717d95ca5", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1a1/1a18eeb47dc365ed18f84fd8cc7c217119d173f42c22f84aad100379293eefb2.mp3", "archive_relative_path": "raw/audio/1a1/1a18eeb47dc365ed18f84fd8cc7c217119d173f42c22f84aad100379293eefb2.mp3" } ] } ], "prediction": "Pugwelg'p na ta'n tujiw pilei.", "reference": "Loqwistaqan eliaq ligpenignigtug." }, { "id": "mic-sent-c9d057ba325ca51648f137ea:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I am growing grass now.", "output_text": "Msigu nige' nigwenm.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I am growing grass now.", "mic_Latn": "Msigu nige' nigwenm." }, "canonical_ref": "entries/n/nigweg/nigweg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7ab1609599b89d7a5e3b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nigweg/nigweg.html", "entry_url": "https://mikmaqonline.org/entries/n/nigweg/nigweg.html", "headword": "nigweg", "example_index": 0, "raw_html_path": "raw/entries/d9ba08467352285306dc2f535d1bb4a67049b8f21425ba0bbfdafbaec23b810e.html", "raw_html_sha256": "578e23c67a1a31ded77f7b39845339d348cc6e99161267214978f20c9828d9a5", "fetched_at": "2026-07-12T02:42:33.017Z", "recordings": [ { "recording_id": "06455124f96795d4128513187c21d81c00db6749b06398aef85e5bec17d0c82b", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/154/15412fdd73516fd20e5015ff9e9b537a56588b4e095e7d98f54234dc00782b93.mp3", "archive_relative_path": "raw/audio/154/15412fdd73516fd20e5015ff9e9b537a56588b4e095e7d98f54234dc00782b93.mp3" } ] } ], "prediction": "Ni'n gi's nige' nuji'j.", "reference": "Msigu nige' nigwenm." }, { "id": "mic-sent-c9e11247e5a0afb514887edf:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend must be ready to have a her baby, her belly's so rotund.", "output_text": "Nitape'sgw etug nugu' unjanit, telmaqapsg'tiat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend must be ready to have a her baby, her belly's so rotund.", "mic_Latn": "Nitape'sgw etug nugu' unjanit, telmaqapsg'tiat." }, "canonical_ref": "entries/m/maqapsg'tiat/maqapsg'tiat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-31a34ee10c74a561a2ac", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/maqapsg'tiat/maqapsg'tiat.html", "entry_url": "https://mikmaqonline.org/entries/m/maqapsg'tiat/maqapsg'tiat.html", "headword": "maqapsg'tiat", "example_index": 0, "raw_html_path": "raw/entries/ee05ffac0197d431a053ed2feb93f6fff20e29f81368e9529f8c993d2d245c82.html", "raw_html_sha256": "cc9ef6ecaeaf390721f35d4cfe300dacf8bcad9bbe74313e2c7b2cb1fb089b03", "fetched_at": "2026-07-12T02:40:49.243Z", "recordings": [ { "recording_id": "30a1914fed8cdc99b4c2012ed26a089695f6374ef214415d593c0166ec6d029e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/17b/17b6285da076af9a2598252aeed4cae33df5e5c40037c5ce770d1ef982a3647c.mp3", "archive_relative_path": "raw/audio/17b/17b6285da076af9a2598252aeed4cae33df5e5c40037c5ce770d1ef982a3647c.mp3" } ] } ], "prediction": "Ula nitap amujpa'latl ugjitl, te's'g ta'n tujiwji'jg.", "reference": "Nitape'sgw etug nugu' unjanit, telmaqapsg'tiat." }, { "id": "mic-sent-ca071d7c81f8d45a3e0b1372:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Peter pushes his buddy across.", "output_text": "Pie'l asoqomigsma'latl witapal.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Peter pushes his buddy across.", "mic_Latn": "Pie'l asoqomigsma'latl witapal." }, "canonical_ref": "entries/a/asoqomigsma'latl/asoqomigsma'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-21ad2996c9097cf182c0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/asoqomigsma'latl/asoqomigsma'latl.html", "entry_url": "https://mikmaqonline.org/entries/a/asoqomigsma'latl/asoqomigsma'latl.html", "headword": "asoqomigsma'latl", "example_index": 0, "raw_html_path": "raw/entries/244a88d424aa4c2899b9e3bf91200efc757772600fd598cf09c4aa8a79f87d94.html", "raw_html_sha256": "c54309e163666b7979c421c4cce4b934df7193870e46f2b7319e48c5605b1613", "fetched_at": "2026-07-12T02:37:21.633Z", "recordings": [ { "recording_id": "814af18afb71f790f5ce5ca98cdc3569d6ae6d2ae314bb64b9e8073d4fab7725", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c5a/c5a4f0dd44dee015128372ab1fd3a65858e361d555f527866936b3d162c1e326.mp3", "archive_relative_path": "raw/audio/c5a/c5a4f0dd44dee015128372ab1fd3a65858e361d555f527866936b3d162c1e326.mp3" } ] } ], "prediction": "Pie'l e'pite'l witapal.", "reference": "Pie'l asoqomigsma'latl witapal." }, { "id": "mic-sent-ca7b331b78d3380d21dc16e3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Daniel, my grandchild is two years old.", "output_text": "Daniel, nuji'j tapuipuna't.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Daniel, my grandchild is two years old.", "mic_Latn": "Daniel, nuji'j tapuipuna't." }, "canonical_ref": "entries/t/tapuipuna't/tapuipuna't.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1562b9dc44d286983120", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tapuipuna't/tapuipuna't.html", "entry_url": "https://mikmaqonline.org/entries/t/tapuipuna't/tapuipuna't.html", "headword": "tapuipuna't", "example_index": 0, "raw_html_path": "raw/entries/e4a573b5cc666cd75ac7aa9521989ed9ef5e80b5e9745c68c14a5f4ed616fc3d.html", "raw_html_sha256": "3e94541f7cd6a65dab0030d94eff7de57f6dad3184c2b71969ca017599a59aa4", "fetched_at": "2026-07-12T02:45:22.646Z", "recordings": [ { "recording_id": "3d7d3b9def4e1f6f9484fac2f1ba9d0bf6f70832897b1c586055780d08649407", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d5a/d5ac52bc65cfc8878feaa188f87244c94341313878ea43909114f627331874a1.mp3", "archive_relative_path": "raw/audio/d5a/d5ac52bc65cfc8878feaa188f87244c94341313878ea43909114f627331874a1.mp3" } ] } ], "prediction": "Ta'ne'l, nuji'j nige' newte'g.", "reference": "Daniel, nuji'j tapuipuna't." }, { "id": "mic-sent-ca82ff96cc8a688156907a32:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she sits where he/she is hidden.", "output_text": "Aqupit ta'n emgopa'sij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she sits where he/she is hidden.", "mic_Latn": "Aqupit ta'n emgopa'sij." }, "canonical_ref": "entries/a/aqupit/aqupit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dda031b4b467fa0ecb03", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/aqupit/aqupit.html", "entry_url": "https://mikmaqonline.org/entries/a/aqupit/aqupit.html", "headword": "aqupit", "example_index": 0, "raw_html_path": "raw/entries/fb7bb1d0505464c47977e8efdf9c4bfd87e2bbc2e76675e40347dc580eb05e16.html", "raw_html_sha256": "dfa273f49ffc96fa61c1d5aeb909613b16272d2a96c7a0a42191d1a713705132", "fetched_at": "2026-07-12T02:37:18.110Z", "recordings": [ { "recording_id": "00ee6e30dfd5e7eb244828a338e05c5186f22f7eff7a9eca1b947e6c1e8084ad", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0ac/0ac3d6aef36338a776362f038da3e290e2c4762252b49f3ad496fa3331b8cc7c.mp3", "archive_relative_path": "raw/audio/0ac/0ac3d6aef36338a776362f038da3e290e2c4762252b49f3ad496fa3331b8cc7c.mp3" } ] } ], "prediction": "E'pite'sit ta'n tujiw gesatg.", "reference": "Aqupit ta'n emgopa'sij." }, { "id": "mic-sent-cab88236acb06a9a2298034c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "You can hear the flapping sound of the window shade.", "output_text": "Lpa nutmn metewaqs'g legepilaqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "You can hear the flapping sound of the window shade.", "mic_Latn": "Lpa nutmn metewaqs'g legepilaqan." }, "canonical_ref": "entries/m/metewaqs'g/metewaqs'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-146c9243524da5bba23d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/metewaqs'g/metewaqs'g.html", "entry_url": "https://mikmaqonline.org/entries/m/metewaqs'g/metewaqs'g.html", "headword": "metewaqs'g", "example_index": 0, "raw_html_path": "raw/entries/09c7202951d3e5c72d70e7943c9528487653138a15a5f62da31508a757adefb4.html", "raw_html_sha256": "d27e35484051ba001e62b07e2c9c5fd68cbe993a717e5b535ada7ed31e9295c8", "fetched_at": "2026-07-12T02:41:26.076Z", "recordings": [ { "recording_id": "597f579c3ca41844d446d8a532e4858416428744baefd659938911fc86cf3c49", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9ae/9aeb1c88ecd07a7b0357664ac6a07c5cf015a2f992ae2290a7e1ed0bd3d29a0f.mp3", "archive_relative_path": "raw/audio/9ae/9aeb1c88ecd07a7b0357664ac6a07c5cf015a2f992ae2290a7e1ed0bd3d29a0f.mp3" } ] } ], "prediction": "Na'te's'g ta'n tujiw gmu'j.", "reference": "Lpa nutmn metewaqs'g legepilaqan." }, { "id": "mic-sent-cae6d875b66e6eee9595bbf6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I think they are light, if you can do it, bring all of them.", "output_text": "Telte'tmann ne'naqji'jgl, gisipgwatu'n ms't jugwa'tu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I think they are light, if you can do it, bring all of them.", "mic_Latn": "Telte'tmann ne'naqji'jgl, gisipgwatu'n ms't jugwa'tu." }, "canonical_ref": "entries/n/ne'naqji'jg/ne'naqji'jg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3caa17ee58b94a16ea6d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ne'naqji'jg/ne'naqji'jg.html", "entry_url": "https://mikmaqonline.org/entries/n/ne'naqji'jg/ne'naqji'jg.html", "headword": "ne'naqji'jg", "example_index": 0, "raw_html_path": "raw/entries/aa2d0726b5ab43fc6d3ade37919c0077b722df42941b63032642e83da27fe5f3.html", "raw_html_sha256": "07ee629187a9b1fbc1c6f7d13549a0a5cf292a9c61089c37af8211de586b1335", "fetched_at": "2026-07-12T02:42:18.729Z", "recordings": [ { "recording_id": "ecf35872a1c487a41f1afaf9d9bc4159b1cc24fda923365a31d7adbc1dd1e1d1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cf8/cf8b3bc1d04102a13fc7b96cd8fedaea06c2fa58c7f6587747549290c0a23f01.mp3", "archive_relative_path": "raw/audio/cf8/cf8b3bc1d04102a13fc7b96cd8fedaea06c2fa58c7f6587747549290c0a23f01.mp3" } ] } ], "prediction": "Telte's'g na'te'l, ge' negm, te's goqwei te'siw.", "reference": "Telte'tmann ne'naqji'jgl, gisipgwatu'n ms't jugwa'tu." }, { "id": "mic-sent-cb4c6d652c2e92117a8f5cde:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she felt all around his/her car looking for his/her glasses.", "output_text": "Ms't utepaqan gis nenatua'toq algwilgl ugpugugwe'l.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she felt all around his/her car looking for his/her glasses.", "mic_Latn": "Ms't utepaqan gis nenatua'toq algwilgl ugpugugwe'l." }, "canonical_ref": "entries/n/nenatua'toq/nenatua'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c133f8ec180a53fadb6f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nenatua'toq/nenatua'toq.html", "entry_url": "https://mikmaqonline.org/entries/n/nenatua'toq/nenatua'toq.html", "headword": "nenatua'toq", "example_index": 0, "raw_html_path": "raw/entries/80b8324d82307b4894927a174e407be8c5be631642d5c3bd7f763bdddf055b3c.html", "raw_html_sha256": "2992fc2f5488e98eb14b4fc259f8e50db2a8471dd37c801f273d523ef3a7fa12", "fetched_at": "2026-07-12T02:36:28.669Z", "recordings": [ { "recording_id": "7551b32c5abbf6194a60629a9643376490f2b2a0b8c19442b15f929af9b18f34", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8da/8daf859231e2d729fad2c322a3e0e8da1dd1af001c001f466116b24a36bff268.mp3", "archive_relative_path": "raw/audio/8da/8daf859231e2d729fad2c322a3e0e8da1dd1af001c001f466116b24a36bff268.mp3" } ] } ], "prediction": "Te's'g na utepaqan ugta'sit.", "reference": "Ms't utepaqan gis nenatua'toq algwilgl ugpugugwe'l." }, { "id": "mic-sent-cb6842748b6968b9fb1ffab7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The skunk stinks.", "output_text": "Apigjilu geslet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The skunk stinks.", "mic_Latn": "Apigjilu geslet." }, "canonical_ref": "entries/g/geslet/geslet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b9562b1217847e09cd67", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/geslet/geslet.html", "entry_url": "https://mikmaqonline.org/entries/g/geslet/geslet.html", "headword": "geslet", "example_index": 0, "raw_html_path": "raw/entries/dee88d54b461542fb912e078bdd915a0c108fc619699f281538841790e671aa4.html", "raw_html_sha256": "120d8cf5d9cbc9f2ace315c2f97c7fa949114316d5df5c732595c582f694e190", "fetched_at": "2026-07-12T02:39:15.151Z", "recordings": [ { "recording_id": "0eff71b1272586637ffc626bd8e4785d92c78c3ef0b265a93b6386293d3dcffb", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cb1/cb1db5233a1edd48a119a2b3a587d7511627e1d46ae9efd1f878fed129d768c4.mp3", "archive_relative_path": "raw/audio/cb1/cb1db5233a1edd48a119a2b3a587d7511627e1d46ae9efd1f878fed129d768c4.mp3" } ] } ], "prediction": "Pugwelg na gmu'j.", "reference": "Apigjilu geslet." }, { "id": "mic-sent-cb72052ccd8acbde85edff03:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My dog really stinks when he farts.", "output_text": "Nti mawigsoqwet ta'n tujiw pittij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My dog really stinks when he farts.", "mic_Latn": "Nti mawigsoqwet ta'n tujiw pittij." }, "canonical_ref": "entries/p/pigtit/pigtit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b217f67345cb6f9d33e0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pigtit/pigtit.html", "entry_url": "https://mikmaqonline.org/entries/p/pigtit/pigtit.html", "headword": "pigtit", "example_index": 0, "raw_html_path": "raw/entries/4b8331a08c86fd2f83bdbd131ec9f7f0ad952dfe21d7d4e9afa811512391a081.html", "raw_html_sha256": "e8d1b24bdf61d3f59b8556f2865d4c1346762c3ac83629351a04c287cf4b6e7e", "fetched_at": "2026-07-12T02:43:54.041Z", "recordings": [ { "recording_id": "62fcbaac377fecd3ed9a0aed3aa5e01a99b22ea3a4e8c9ac51a30bd902f1d7a9", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8ef/8ef4831471c9eafd6094806682be15328f466d48d3e201cffce6d0bfd98c1fcf.mp3", "archive_relative_path": "raw/audio/8ef/8ef4831471c9eafd6094806682be15328f466d48d3e201cffce6d0bfd98c1fcf.mp3" } ] } ], "prediction": "Nmu'ji'j gesatg ta'n tujiw gisijig.", "reference": "Nti mawigsoqwet ta'n tujiw pittij." }, { "id": "mic-sent-cc31205702b24d82c65caf1e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend is not feeling well, he thinks he is swelling up.", "output_text": "Nitap mu weleiug, teltasit put'pegiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend is not feeling well, he thinks he is swelling up.", "mic_Latn": "Nitap mu weleiug, teltasit put'pegiet." }, "canonical_ref": "entries/p/put'pegiet/put'pegiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1ea1b897f6e9e1b3085b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/put'pegiet/put'pegiet.html", "entry_url": "https://mikmaqonline.org/entries/p/put'pegiet/put'pegiet.html", "headword": "put'pegiet", "example_index": 0, "raw_html_path": "raw/entries/4d898af87d52c70ddea4af03b7cf8071cd6131c8d743fc481cee8f2a60217408.html", "raw_html_sha256": "14c354e81912c7e914dbaf012965f11953dfe10687cee923d739a9671199f6a7", "fetched_at": "2026-07-12T02:44:30.908Z", "recordings": [ { "recording_id": "0ce68d733bf682c6f9a4cd0aee58230f2b728ae9c7a6fa4475f0191368a7a1ca", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5fd/5fd8c870996d22fd92ad387c13feaf1f36ec5128aeb6d4b765df40935b42582c.mp3", "archive_relative_path": "raw/audio/5fd/5fd8c870996d22fd92ad387c13feaf1f36ec5128aeb6d4b765df40935b42582c.mp3" } ] } ], "prediction": "Ula nitap mu gesatg, telte's'g etlmisga'toq.", "reference": "Nitap mu weleiug, teltasit put'pegiet." }, { "id": "mic-sent-cccba9519dc72fa5aae2d0a9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I wonder what sort of houses we will live in when we grow up?", "output_text": "Etug tali'guomgnmultitesnu gisiguti'gw?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I wonder what sort of houses we will live in when we grow up?", "mic_Latn": "Etug tali'guomgnmultitesnu gisiguti'gw?" }, "canonical_ref": "entries/t/tali'guomgnmit/tali'guomgnmit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-baa3302d27b9296cce7d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tali'guomgnmit/tali'guomgnmit.html", "entry_url": "https://mikmaqonline.org/entries/t/tali'guomgnmit/tali'guomgnmit.html", "headword": "tali'guomgnmit", "example_index": 0, "raw_html_path": "raw/entries/c3da7287c02cde8a8d0c7d787fd68a2106e11388349ee68f97997b7a2aa0abbb.html", "raw_html_sha256": "669dfb8bc06c09e3e3468f40bd1e54fd7f7dc1804139b03a6ae1cf6410013c5b", "fetched_at": "2026-07-12T02:36:27.161Z", "recordings": [ { "recording_id": "5986f2023a7bb3c463b0a88dba276dd47ab4c803fc546a95082b07d9cb903bfa", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5de/5de7632cccafe729c34f8021c38cd4ce343da27d8e1e23a4c4cb3072f0cf66f4.mp3", "archive_relative_path": "raw/audio/5de/5de7632cccafe729c34f8021c38cd4ce343da27d8e1e23a4c4cb3072f0cf66f4.mp3" } ] } ], "prediction": "Ta'n tujiw ta'n te's'g na'te'l?", "reference": "Etug tali'guomgnmultitesnu gisiguti'gw?" }, { "id": "mic-sent-cd3bc8677710046a31a9b050:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/She was so surprised when he/she heard the news, his/her mouth really was gaping open.", "output_text": "Telpa'qalaig nutmateg, lpa gjitmei pantuno'jing.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/She was so surprised when he/she heard the news, his/her mouth really was gaping open.", "mic_Latn": "Telpa'qalaig nutmateg, lpa gjitmei pantuno'jing." }, "canonical_ref": "entries/p/pantuno'jing/pantuno'jing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d7eb580b3808856b80b2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pantuno'jing/pantuno'jing.html", "entry_url": "https://mikmaqonline.org/entries/p/pantuno'jing/pantuno'jing.html", "headword": "pantuno'jing", "example_index": 0, "raw_html_path": "raw/entries/f944c975b2719ef0104a5d3fb8f5a141deed016bf4b7cdecad278bd894490d2f.html", "raw_html_sha256": "d63b7770aa6bc86de48dab7183bf43823d0ac1d09e94b2948a5138440955f1fa", "fetched_at": "2026-07-12T02:43:07.591Z", "recordings": [ { "recording_id": "da377bf625a69be94ff0c6491a9cf0c827859f540657524335343695d96828f7", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0a2/0a29add13bf6b3e77629dce58d1770e5f1640c3f4d37abb1e2eb9fdc5a66a9ee.mp3", "archive_relative_path": "raw/audio/0a2/0a29add13bf6b3e77629dce58d1770e5f1640c3f4d37abb1e2eb9fdc5a66a9ee.mp3" } ] } ], "prediction": "Tetuji'jg ta'n tujiw nujiw, lpa we'gwi'g.", "reference": "Telpa'qalaig nutmateg, lpa gjitmei pantuno'jing." }, { "id": "mic-sent-cda828b5e706b61e2ff31288:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A cedar shingled house has a great look.", "output_text": "Pugsaqte'gna'tas'g wenji'guom mawuliangamgug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A cedar shingled house has a great look.", "mic_Latn": "Pugsaqte'gna'tas'g wenji'guom mawuliangamgug." }, "canonical_ref": "entries/p/pugsaqte'gn/pugsaqte'gn.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-528936169e86cfd03e64", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pugsaqte'gn/pugsaqte'gn.html", "entry_url": "https://mikmaqonline.org/entries/p/pugsaqte'gn/pugsaqte'gn.html", "headword": "pugsaqte'gn", "example_index": 0, "raw_html_path": "raw/entries/16059726c858a8e3f9ad8dd36ebb1ca974e8f8452c86b9a6d185c62748172bd0.html", "raw_html_sha256": "afee7889e0bfaf8b9c65bcd71212a4191a59da21cbd8f20ed2339a34eca97e5f", "fetched_at": "2026-07-12T02:44:21.347Z", "recordings": [ { "recording_id": "0d3751cecac830f44149c2d0249903d9137bd227169d05ee204d3a5059113b1c", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/36f/36f025b734c9793859cdcfc611c4a71a93313362b62cee37f25859a9cc5e1539.mp3", "archive_relative_path": "raw/audio/36f/36f025b734c9793859cdcfc611c4a71a93313362b62cee37f25859a9cc5e1539.mp3" } ] } ], "prediction": "We'gwi'jg na we'gwigtug.", "reference": "Pugsaqte'gna'tas'g wenji'guom mawuliangamgug." }, { "id": "mic-sent-cdeb98121a4d38e798ab13b0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The photograph is torn.", "output_text": "Temine'g napui'gign.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The photograph is torn.", "mic_Latn": "Temine'g napui'gign." }, "canonical_ref": "entries/t/temine'g/temine'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-cfc1df8746e5280fe608", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/temine'g/temine'g.html", "entry_url": "https://mikmaqonline.org/entries/t/temine'g/temine'g.html", "headword": "temine'g", "example_index": 0, "raw_html_path": "raw/entries/2a8c85a24ffeb1d2bb6f530cd5146a2a0959c859719e386d337d1138c93553ef.html", "raw_html_sha256": "382159c06605c0c3f538e75f30c4fe6c2541ad21a9d5bdd8cd1ffacad1ac9815", "fetched_at": "2026-07-12T02:45:38.746Z", "recordings": [ { "recording_id": "58d114859362b5a2ed2e842a57b6550d5ddd336a915444d7e7e660fc3bcdaa5a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/839/83981b9c22075645fd06c9439379547120a3e6c1495d70b3e16f1ea3f0c4645c.mp3", "archive_relative_path": "raw/audio/839/83981b9c22075645fd06c9439379547120a3e6c1495d70b3e16f1ea3f0c4645c.mp3" } ] } ], "prediction": "Pugwelg na foto'gwe'g.", "reference": "Temine'g napui'gign." }, { "id": "mic-sent-cdfaf6dce56460aac790cb56:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Do you remember the first time you went to a school?", "output_text": "Migwite'tmn amgweseweieg elieneg nujigina'muo'guom?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Do you remember the first time you went to a school?", "mic_Latn": "Migwite'tmn amgweseweieg elieneg nujigina'muo'guom?" }, "canonical_ref": "entries/n/nujigina'muo'guom/nujigina'muo'guom.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-981ccca16b91f4919f80", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nujigina'muo'guom/nujigina'muo'guom.html", "entry_url": "https://mikmaqonline.org/entries/n/nujigina'muo'guom/nujigina'muo'guom.html", "headword": "nujigina'muo'guom", "example_index": 0, "raw_html_path": "raw/entries/5f182122a86cd5810b8e4855bf941c66cfe006258fc210b48263267b022cd418.html", "raw_html_sha256": "7987b45e03027a34a7534137ccadb45bdd35ca9b9a1ba8513be44e9702996670", "fetched_at": "2026-07-12T02:42:49.494Z", "recordings": [ { "recording_id": "499b30e2b88dd95b673aa9e3163e5dc703be750c6e63db3a49fd96c2f08829e6", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a82/a820e344da0bcc018a03003ca5b673a3cb2cab724b0a21851ae87e1651a5d2aa.mp3", "archive_relative_path": "raw/audio/a82/a820e344da0bcc018a03003ca5b673a3cb2cab724b0a21851ae87e1651a5d2aa.mp3" } ] } ], "prediction": "Gi's gi's nige' pas'g gisipugwet?", "reference": "Migwite'tmn amgweseweieg elieneg nujigina'muo'guom?" }, { "id": "mic-sent-ce0153a6e359fee7c10c5d78:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she can always be relied on to work with precision.", "output_text": "Apjiw negm gisilita'simg giasgilugwen.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she can always be relied on to work with precision.", "mic_Latn": "Apjiw negm gisilita'simg giasgilugwen." }, "canonical_ref": "entries/g/giasgilugwet/giasgilugwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-23d9aac15a527b87f6ba", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/giasgilugwet/giasgilugwet.html", "entry_url": "https://mikmaqonline.org/entries/g/giasgilugwet/giasgilugwet.html", "headword": "giasgilugwet", "example_index": 0, "raw_html_path": "raw/entries/2fbfa95b9c4c046f7e1d89f4adcf37a38e0a97ea4e3cbf35dbd2f7a41e3cefa5.html", "raw_html_sha256": "1cf667c2feeb89536c95f9c4d89d0cd140800914d95284094fe0c755d8e23ba5", "fetched_at": "2026-07-12T02:39:27.308Z", "recordings": [ { "recording_id": "bf33a29db75d7a9a0edbacab2df829c8b2e3db97d32a355e9c5aef73b0c5bd0b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/edc/edc13ce326e991dca2c02fbc4b0f2cd49056db0b93056dc0752535aea9325bcd.mp3", "archive_relative_path": "raw/audio/edc/edc13ce326e991dca2c02fbc4b0f2cd49056db0b93056dc0752535aea9325bcd.mp3" } ] } ], "prediction": "Te'sipow ta'n tujiw gisiwugwet.", "reference": "Apjiw negm gisilita'simg giasgilugwen." }, { "id": "mic-sent-ce1c43b844da68488d143c59:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I would really like it if I could hear the sound made by the great horned owl.", "output_text": "Etna'gsatmug gis nutaqas ta'n teltoqsij ti'tigli.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I would really like it if I could hear the sound made by the great horned owl.", "mic_Latn": "Etna'gsatmug gis nutaqas ta'n teltoqsij ti'tigli." }, "canonical_ref": "entries/t/ti'tigli/ti'tigli.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d2e044934f63abc6b99a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/ti'tigli/ti'tigli.html", "entry_url": "https://mikmaqonline.org/entries/t/ti'tigli/ti'tigli.html", "headword": "ti'tigli", "example_index": 0, "raw_html_path": "raw/entries/879c2396b4c9e3e63cb09ce2d90d9cda073f672b7e20c86ab5c56e1a30f219e4.html", "raw_html_sha256": "eb64ad0f16603c3e101eb2f9ab8fc7e6c08ed004be014ce75e4fbb87cc122af6", "fetched_at": "2026-07-12T02:45:58.348Z", "recordings": [ { "recording_id": "2d7879bd09fa2a43f2107792269172b88dbd2a98c6a608247549a6c1c59e3a46", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/399/399966a5bdf8e9456f11411fdd539123be402bbb569ef9dc8093cfce981d82de.mp3", "archive_relative_path": "raw/audio/399/399966a5bdf8e9456f11411fdd539123be402bbb569ef9dc8093cfce981d82de.mp3" } ] } ], "prediction": "We'gwi'g ta'n tujiw nugu' gmu'ji'j.", "reference": "Etna'gsatmug gis nutaqas ta'n teltoqsij ti'tigli." }, { "id": "mic-sent-ce6be000f4b33ce5eda92b36:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Has anyone brought in their belongings.", "output_text": "Gi's wen pisgwa'toq utapsun?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Has anyone brought in their belongings.", "mic_Latn": "Gi's wen pisgwa'toq utapsun?" }, "canonical_ref": "entries/p/pisgwa'toq/pisgwa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-45c0c090dd6e87a42266", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pisgwa'toq/pisgwa'toq.html", "entry_url": "https://mikmaqonline.org/entries/p/pisgwa'toq/pisgwa'toq.html", "headword": "pisgwa'toq", "example_index": 0, "raw_html_path": "raw/entries/5c837437409c5bb32733c6739d273eb239268276a1297d6179cd1ba11d5fa6cf.html", "raw_html_sha256": "f09417582025dad4fd2cc1f6de2bdcba62a15cf4e229f4e72aeba1597e4b8a82", "fetched_at": "2026-07-12T02:44:03.261Z", "recordings": [ { "recording_id": "6ed4c4fdda4f0ec26d179c0a05a05e2056ebdc2094ef76273441875eeada4a52", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c91/c91b018c8a907c7373883f2c338521d215fff23692ceee79523101b245dbe5cc.mp3", "archive_relative_path": "raw/audio/c91/c91b018c8a907c7373883f2c338521d215fff23692ceee79523101b245dbe5cc.mp3" } ] } ], "prediction": "Gi's gi'l we'gwigtug ugjit.", "reference": "Gi's wen pisgwa'toq utapsun?" }, { "id": "mic-sent-ce82f150359c31d42c4be1fb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "To get to the road I had to shovel my path out today.", "output_text": "Ta'n telmatama'si gisgug amujpa qalipitm ntawti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "To get to the road I had to shovel my path out today.", "mic_Latn": "Ta'n telmatama'si gisgug amujpa qalipitm ntawti." }, "canonical_ref": "entries/q/qalipitg/qalipitg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3af0166ac0a597eab8eb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/q/qalipitg/qalipitg.html", "entry_url": "https://mikmaqonline.org/entries/q/qalipitg/qalipitg.html", "headword": "qalipitg", "example_index": 0, "raw_html_path": "raw/entries/72a87b5584148c4d339fa2dfe95bb4617781d718bf0c7776884356667005d410.html", "raw_html_sha256": "0adea558e7ba043d7bc035b83c7cd6211e5fd5452847b1416419cce905b79cab", "fetched_at": "2026-07-12T02:44:31.707Z", "recordings": [ { "recording_id": "752bab9226450299efdde321e67b1b5985e1b760cb811af5857c264b68a17c93", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b8e/b8eef26a87a008d24a2507902484c9e39bd9a7e329f059589334cdcdc99d8b13.mp3", "archive_relative_path": "raw/audio/b8e/b8eef26a87a008d24a2507902484c9e39bd9a7e329f059589334cdcdc99d8b13.mp3" } ] } ], "prediction": "Amujpa we'gwi's'g gisgug amujpa'toq ntul.", "reference": "Ta'n telmatama'si gisgug amujpa qalipitm ntawti." }, { "id": "mic-sent-ceae27c8f6cef59baeb49390:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is limping, he/she must have sprained his/her big toe.", "output_text": "Aliasgaja't, etug gisio'plisqatestoq ugmaqaqjigeweim.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is limping, he/she must have sprained his/her big toe.", "mic_Latn": "Aliasgaja't, etug gisio'plisqatestoq ugmaqaqjigeweim." }, "canonical_ref": "entries/o/o'plisqatestoq/o'plisqatestoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-17ef6da2323e8070eb27", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/o/o'plisqatestoq/o'plisqatestoq.html", "entry_url": "https://mikmaqonline.org/entries/o/o'plisqatestoq/o'plisqatestoq.html", "headword": "o'plisqatestoq", "example_index": 0, "raw_html_path": "raw/entries/e355af3242643e18250ac973a25d70df2b6ec9f311099fc50fa72f2263ba6f16.html", "raw_html_sha256": "eb84dee2d9c3f919f12269cfd1fb033ef2fd620917fce375243151d72580a8fe", "fetched_at": "2026-07-12T02:43:00.059Z", "recordings": [ { "recording_id": "27b6dbac280338093b39081d074636a6292d260ab6cee3acc88a1d13a51ce50b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cad/cad860c8d3fbcb565f6f4bff3b6aafe79f3acd7ae4aee7e4cf18a960aa3a1bac.mp3", "archive_relative_path": "raw/audio/cad/cad860c8d3fbcb565f6f4bff3b6aafe79f3acd7ae4aee7e4cf18a960aa3a1bac.mp3" } ] } ], "prediction": "Gesatg, amujpa gesatg ugta'qann.", "reference": "Aliasgaja't, etug gisio'plisqatestoq ugmaqaqjigeweim." }, { "id": "mic-sent-cf6976a72e545f82262cb4d9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The checkered shirt is new.", "output_text": "Atnaqan wi'gasit pilei atla'i.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The checkered shirt is new.", "mic_Latn": "Atnaqan wi'gasit pilei atla'i." }, "canonical_ref": "entries/a/atnaqan_wi'gasit/atnaqan_wi'gasit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8c2d04efc1cd13187821", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/atnaqan_wi'gasit/atnaqan_wi'gasit.html", "entry_url": "https://mikmaqonline.org/entries/a/atnaqan_wi'gasit/atnaqan_wi'gasit.html", "headword": "atnaqan_wi'gasit", "example_index": 0, "raw_html_path": "raw/entries/d3f31b66bdd24c2d53a9c09d4d0d7e3d67d8ca53e9d8d15eb9081d0ef6c0203b.html", "raw_html_sha256": "15f5aff4d3414858fcea86bb5a48e16df674775d92bc80fe767a6eef30fe0db0", "fetched_at": "2026-07-12T02:37:26.250Z", "recordings": [ { "recording_id": "a433a663d19e1d2b15fdf2e42d87a24b617876566bcca9fefac47f922d0eca3f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0b4/0b477649a6d6bb513d9bbe15676a1532b5d6b11bd8a852a55ee0557db581d558.mp3", "archive_relative_path": "raw/audio/0b4/0b477649a6d6bb513d9bbe15676a1532b5d6b11bd8a852a55ee0557db581d558.mp3" } ] } ], "prediction": "Pilei'g pilei newte'g.", "reference": "Atnaqan wi'gasit pilei atla'i." }, { "id": "mic-sent-cf79aabe566665fa76222b9f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Je'g has a fire going in the back.", "output_text": "Je'g pugte'nmat ugtejg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Je'g has a fire going in the back.", "mic_Latn": "Je'g pugte'nmat ugtejg." }, "canonical_ref": "entries/p/pugte_nmat/pugte_nmat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0bba5cd7f5289cdb6094", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pugte_nmat/pugte_nmat.html", "entry_url": "https://mikmaqonline.org/entries/p/pugte_nmat/pugte_nmat.html", "headword": "pugte’nmat", "example_index": 0, "raw_html_path": "raw/entries/11d42025ead9fb61f2ebd6020329effd1c17a772a5e8f8ebb15c3279ad56a825.html", "raw_html_sha256": "df1df5a651aa95042a9a46afc7366e3e431e53b130da380e4cd3c5a710dcdf7c", "fetched_at": "2026-07-12T02:36:17.897Z", "recordings": [ { "recording_id": "d36dff2d6292a08cd499dcb169ddc8e79ea3934fb25fce9db4f56eeb0b39907a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a96/a968291fa7bc8f598740b87ef2fa6343b95ea5e156e226c47b1cff66826227c2.mp3", "archive_relative_path": "raw/audio/a96/a968291fa7bc8f598740b87ef2fa6343b95ea5e156e226c47b1cff66826227c2.mp3" } ] } ], "prediction": "Je'g etlmisga'toq ugjit.", "reference": "Je'g pugte'nmat ugtejg." }, { "id": "mic-sent-cf8823e61dea3f8ea667a17d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "John is from Elsipugtug.", "output_text": "Sa'n wetapaqamit Elsipugtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "John is from Elsipugtug.", "mic_Latn": "Sa'n wetapaqamit Elsipugtug." }, "canonical_ref": "entries/w/wetapaqamit/wetapaqamit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-28400459fc24b05bac66", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wetapaqamit/wetapaqamit.html", "entry_url": "https://mikmaqonline.org/entries/w/wetapaqamit/wetapaqamit.html", "headword": "wetapaqamit", "example_index": 0, "raw_html_path": "raw/entries/e163b58370678931a69115039a54a9b821f0098c226ec2b14579d2c22ac72e39.html", "raw_html_sha256": "359a4c46c682e3f7a643724a7288fde62a89b58642d02110fff76ca648685810", "fetched_at": "2026-07-12T02:47:23.482Z", "recordings": [ { "recording_id": "eab1bde224481880278f1282f0f8624b209a20005d6dd21d13bf9bdc5e24b3f1", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/423/42344dd1119c98ae182f77aa6bb2e87814328d78c3ec25d3551e9e2351295600.mp3", "archive_relative_path": "raw/audio/423/42344dd1119c98ae182f77aa6bb2e87814328d78c3ec25d3551e9e2351295600.mp3" } ] } ], "prediction": "Sa'n na Elsipugtugtug.", "reference": "Sa'n wetapaqamit Elsipugtug." }, { "id": "mic-sent-cfd69b368d4fa31636bd1bd2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I guess it is nice to see him/her again, you haven't seen each other for such a long time.", "output_text": "Miamuj pe'gwamugsit, tewji sa'q mu nemi'tiwoq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I guess it is nice to see him/her again, you haven't seen each other for such a long time.", "mic_Latn": "Miamuj pe'gwamugsit, tewji sa'q mu nemi'tiwoq." }, "canonical_ref": "entries/p/pe'gwamugsit/pe'gwamugsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f17723fbe844ddf73029", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pe'gwamugsit/pe'gwamugsit.html", "entry_url": "https://mikmaqonline.org/entries/p/pe'gwamugsit/pe'gwamugsit.html", "headword": "pe'gwamugsit", "example_index": 0, "raw_html_path": "raw/entries/9b772d1b191e2d3e2417ab5fb5037cce48adac7b0f6bf7ea208071af696a4bd3.html", "raw_html_sha256": "93baa126a2622173d90bc2ac3fbe08983f12046c24758907e45561e570902818", "fetched_at": "2026-07-12T02:43:22.964Z", "recordings": [ { "recording_id": "85b1f2853bbc44537d22acadbbb037412071196e421b4e85981a2911003a6b66", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/292/292a9b454e9ad51d5eff260eb7d569f878dfb86b3a2fa0664b7bfaebf0b39e27.mp3", "archive_relative_path": "raw/audio/292/292a9b454e9ad51d5eff260eb7d569f878dfb86b3a2fa0664b7bfaebf0b39e27.mp3" } ] } ], "prediction": "Telte's'g we'gwi'g, mu telte'g ta'n tujiw nemita'sit.", "reference": "Miamuj pe'gwamugsit, tewji sa'q mu nemi'tiwoq." }, { "id": "mic-sent-cfe3ba0bc2553a88cd254520:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This ladder he/she made is so lopsided.", "output_text": "Ula lgusuaqan gisitoq lpa ugumejig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This ladder he/she made is so lopsided.", "mic_Latn": "Ula lgusuaqan gisitoq lpa ugumejig." }, "canonical_ref": "entries/u/ugumejig/ugumejig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b2ca0a766615c63c8da1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugumejig/ugumejig.html", "entry_url": "https://mikmaqonline.org/entries/u/ugumejig/ugumejig.html", "headword": "ugumejig", "example_index": 0, "raw_html_path": "raw/entries/9b193aa32145433b8fbce2e2d94daa7809045922d12000672fcfc94da1523c09.html", "raw_html_sha256": "11f4c259f2f6aab47019133cd6ebe19ec834b2912f285f75f02cec77ab8cdaec", "fetched_at": "2026-07-12T02:46:20.651Z", "recordings": [ { "recording_id": "e90caace4df85b29ff075d8ca915d8b45f4649caaf4dc448e52e07c37a9e802c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e06/e06522d4006ea7a925e17ab74fc979a96120182f346c31c914105607e42e7849.mp3", "archive_relative_path": "raw/audio/e06/e06522d4006ea7a925e17ab74fc979a96120182f346c31c914105607e42e7849.mp3" } ] } ], "prediction": "Tetuji'jg na ula lpaqan.", "reference": "Ula lgusuaqan gisitoq lpa ugumejig." }, { "id": "mic-sent-d024ebd1525b1e1fb8cd60e6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is ready just now, he/she wants to go home.", "output_text": "Assma nige' gisgaje'g, getu'nmiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is ready just now, he/she wants to go home.", "mic_Latn": "Assma nige' gisgaje'g, getu'nmiet." }, "canonical_ref": "entries/g/getu'nmiet/getu'nmiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6fd2c957699d94410fd3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/getu'nmiet/getu'nmiet.html", "entry_url": "https://mikmaqonline.org/entries/g/getu'nmiet/getu'nmiet.html", "headword": "getu'nmiet", "example_index": 0, "raw_html_path": "raw/entries/0417cee4ccba0fa77b8884ebaccbca9f5d3cfd45a113b4837538f99b3b956df3.html", "raw_html_sha256": "d74235eb9cf751c39ccb2176c02ec5bb3a172645b03d9c86ee8eee448f96815c", "fetched_at": "2026-07-12T02:39:25.194Z", "recordings": [ { "recording_id": "27f28ac69cfc8ff6463e5328dbdff65fac9fb49952c856b34860f2af8f116c72", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f79/f7989638037a90f8985d9ca99f91eb5752d16143f0d8921486684604be148974.mp3", "archive_relative_path": "raw/audio/f79/f7989638037a90f8985d9ca99f91eb5752d16143f0d8921486684604be148974.mp3" } ] } ], "prediction": "Gi's gi's nige' pas'g, poqji'j.", "reference": "Assma nige' gisgaje'g, getu'nmiet." }, { "id": "mic-sent-d0581f55de56ccb20da486c9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she comes crying and says he/she lost his/her candy.", "output_text": "Wejgwatemit aq teluet entoqigl ugsuitismgl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she comes crying and says he/she lost his/her candy.", "mic_Latn": "Wejgwatemit aq teluet entoqigl ugsuitismgl." }, "canonical_ref": "entries/w/wejgwatemit/wejgwatemit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5dce8633eb112411ac2d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejgwatemit/wejgwatemit.html", "entry_url": "https://mikmaqonline.org/entries/w/wejgwatemit/wejgwatemit.html", "headword": "wejgwatemit", "example_index": 0, "raw_html_path": "raw/entries/8d141f17d9f18b107c0621d51f38b8ab8a4a27a8b0e717f8f02ff2d7ae155409.html", "raw_html_sha256": "ea33df8fa13fc4c1f035f5cd5319221c6e12db659268e68044a315ac5b249b72", "fetched_at": "2026-07-12T02:36:11.087Z", "recordings": [ { "recording_id": "2b21907394fcb8a690273d7e4bc223719e677c213f67aab56417bd3d63968481", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5ba/5ba478de6e94e03b37e4daad21a152cd343a5ec77dfcd7276f9b716a52f01900.mp3", "archive_relative_path": "raw/audio/5ba/5ba478de6e94e03b37e4daad21a152cd343a5ec77dfcd7276f9b716a52f01900.mp3" } ] } ], "prediction": "Pugwelg'p aq telte's'g ugjit ugjit.", "reference": "Wejgwatemit aq teluet entoqigl ugsuitismgl." }, { "id": "mic-sent-d164325e62b1bcd379a00db9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A male westerner is here to visit us, and he has arrived with food from his homeland for us.", "output_text": "Tg'snugowa'j pejimittugwalugsieg, aq mijipjewei um'tgigewei pegisitugsieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A male westerner is here to visit us, and he has arrived with food from his homeland for us.", "mic_Latn": "Tg'snugowa'j pejimittugwalugsieg, aq mijipjewei um'tgigewei pegisitugsieg." }, "canonical_ref": "entries/t/tg'snugowa'j/tg'snugowa'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2ae4795bb3971fba73b8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tg'snugowa'j/tg'snugowa'j.html", "entry_url": "https://mikmaqonline.org/entries/t/tg'snugowa'j/tg'snugowa'j.html", "headword": "tg'snugowa'j", "example_index": 0, "raw_html_path": "raw/entries/50a696c112d0e225cf1f33cd311428dba56d413b9cfec521bb0379f1c6827486.html", "raw_html_sha256": "abb2558f846f5c9fd77984ff7e5428a640f679e3b32449a96fd80000a7cacc23", "fetched_at": "2026-07-12T02:45:56.538Z", "recordings": [ { "recording_id": "ff0184715e5899d8b3f5a2bb1e90e274d75028d5079bd048246c8868dea97f41", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cc0/cc06b1e0da1f897549a4e7d415a1aa3b766026590ae937038e38f50d9fedd105.mp3", "archive_relative_path": "raw/audio/cc0/cc06b1e0da1f897549a4e7d415a1aa3b766026590ae937038e38f50d9fedd105.mp3" } ] } ], "prediction": "We'gwi'ji'jig ula tet, aq gisi'gwatg ugjit ugjit.", "reference": "Tg'snugowa'j pejimittugwalugsieg, aq mijipjewei um'tgigewei pegisitugsieg." }, { "id": "mic-sent-d16f0a70d4c9fdb05fb71a85:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This youngster is neat and tidy.", "output_text": "Ula maljewe'j waqamnmat.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This youngster is neat and tidy.", "mic_Latn": "Ula maljewe'j waqamnmat." }, "canonical_ref": "entries/w/waqamnmat/waqamnmat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-27cb9240b8ec107a2b4a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/waqamnmat/waqamnmat.html", "entry_url": "https://mikmaqonline.org/entries/w/waqamnmat/waqamnmat.html", "headword": "waqamnmat", "example_index": 0, "raw_html_path": "raw/entries/a11cf0b8a44584523aa678e59ac825fba538b4cc1aac2948343bab8114fa3f05.html", "raw_html_sha256": "668360a0f20ea5fefa7ea523fcd4f4cb6a7dab512bad48b8b42fae9518b1eada", "fetched_at": "2026-07-12T02:46:38.816Z", "recordings": [ { "recording_id": "2ed69fb4b0e01e048dc5fd5567169348dde37fe1c218d8db8567f73903d430a0", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f78/f78a36e77e99a2617d3bc016fd50146d1162fdd79704ef80ac01250ce6db12d7.mp3", "archive_relative_path": "raw/audio/f78/f78a36e77e99a2617d3bc016fd50146d1162fdd79704ef80ac01250ce6db12d7.mp3" } ] } ], "prediction": "Ula ji'nmji'j na we'gwi'j.", "reference": "Ula maljewe'j waqamnmat." }, { "id": "mic-sent-d1711bc543afee7308433dc1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary made some fast money on Tuesday.", "output_text": "Mali gis(i)jaqalte'g suliewei Ta'puoweieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary made some fast money on Tuesday.", "mic_Latn": "Mali gis(i)jaqalte'g suliewei Ta'puoweieg." }, "canonical_ref": "entries/j/jaqalte'g/jaqalte'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-063c2f2f64a5652732a2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jaqalte'g/jaqalte'g.html", "entry_url": "https://mikmaqonline.org/entries/j/jaqalte'g/jaqalte'g.html", "headword": "jaqalte'g", "example_index": 0, "raw_html_path": "raw/entries/d926c80ce4d9f131bfd0eafffaee7fcbe488229800e7eb574c44e867c8534f10.html", "raw_html_sha256": "bab437abbc502d617d6115d2cb04008c94cc6443fa97c03f1d1a0e98cdb8eecf", "fetched_at": "2026-07-12T02:40:15.493Z", "recordings": [ { "recording_id": "b7bf092175e005aa35ad5032864f36174c901a7939a0128d39f0197435302383", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e14/e143230fc111781864eaceffad5660aab71cc75ac109e73c6516b673215e1417.mp3", "archive_relative_path": "raw/audio/e14/e143230fc111781864eaceffad5660aab71cc75ac109e73c6516b673215e1417.mp3" } ] } ], "prediction": "Mali na'te's'g ugjit nige' gisgug.", "reference": "Mali gis(i)jaqalte'g suliewei Ta'puoweieg." }, { "id": "mic-sent-d184fa73a59933e6749d0a85:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she uses a horse and slowly pulls his/her car.", "output_text": "Te'sipowl e'watl aq sangew wetnng utepaqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she uses a horse and slowly pulls his/her car.", "mic_Latn": "Te'sipowl e'watl aq sangew wetnng utepaqan." }, "canonical_ref": "entries/w/wetnng/wetnng.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1b6416412f372734a0c0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wetnng/wetnng.html", "entry_url": "https://mikmaqonline.org/entries/w/wetnng/wetnng.html", "headword": "wetnng", "example_index": 0, "raw_html_path": "raw/entries/bcc15466956eebc34ef6eca08f9fdb398160a6480448e2b2b798e171eaf3989a.html", "raw_html_sha256": "a8b61b642a8312a16b4e78b01ed5fa5840992542ce7109e85786985dfa055981", "fetched_at": "2026-07-12T02:47:25.684Z", "recordings": [ { "recording_id": "63b5703cfcca33d56f2b3fd9bb2624d86c458305e9171f367a263951a410312a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e81/e81b0f2cec830de990dd9f3259662cf1712eea795a7169b42857cc7c79477430.mp3", "archive_relative_path": "raw/audio/e81/e81b0f2cec830de990dd9f3259662cf1712eea795a7169b42857cc7c79477430.mp3" } ] } ], "prediction": "E'pite'g ugt'p aq maljewe'g utepaqan.", "reference": "Te'sipowl e'watl aq sangew wetnng utepaqan." }, { "id": "mic-sent-d1cabee5d24e094c6c08f25a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "As usual here's John Peter's car going by making noise.", "output_text": "Gi's pana ula San Pie'l utepaqan pemta'q.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "As usual here's John Peter's car going by making noise.", "mic_Latn": "Gi's pana ula San Pie'l utepaqan pemta'q." }, "canonical_ref": "entries/p/pemta'q/pemta'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-fefb856425daf9e699c9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemta'q/pemta'q.html", "entry_url": "https://mikmaqonline.org/entries/p/pemta'q/pemta'q.html", "headword": "pemta'q", "example_index": 0, "raw_html_path": "raw/entries/204c936832dae95afa66f62a1b240cd9ad43dd40fb6759be850c478c324f2b9b.html", "raw_html_sha256": "83eb11c5e22ac580f6ad418895a5215a9d99826e6fce7a452329595ae69270de", "fetched_at": "2026-07-12T02:43:37.143Z", "recordings": [ { "recording_id": "553e852a064200b9edfd880cdb16ed24284cc52caf9b54468f74b95741d7d8b2", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/943/94332fa5ad07fffb46a3b2e83ca408db2bd6f6ac68ebb3248228b06aa5624744.mp3", "archive_relative_path": "raw/audio/943/94332fa5ad07fffb46a3b2e83ca408db2bd6f6ac68ebb3248228b06aa5624744.mp3" } ] } ], "prediction": "Gi's gi's ula ta'n Sa'n Pie'l utepaqan.", "reference": "Gi's pana ula San Pie'l utepaqan pemta'q." }, { "id": "mic-sent-d23241ccbbf5a59e3122825c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Hold on, wait for me!", "output_text": "Ge's'g, pe'l esgmali!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Hold on, wait for me!", "mic_Latn": "Ge's'g, pe'l esgmali!" }, "canonical_ref": "entries/g/ge's'g/ge's'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a21d0173997a383844f9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/ge's'g/ge's'g.html", "entry_url": "https://mikmaqonline.org/entries/g/ge's'g/ge's'g.html", "headword": "ge's'g", "example_index": 0, "raw_html_path": "raw/entries/8c10f52d35c04debbe1960e9f54eeae5880d833fe4011cc9bf560b24ed960377.html", "raw_html_sha256": "fe45349dde78607e905eb7e1d693075e91a0ffc8d3f14c37f72ecbc8b0e47ae6", "fetched_at": "2026-07-12T02:39:03.703Z", "recordings": [ { "recording_id": "6d4c4864da6d8e08c9d3c6b399e55da8b9bd1def55f124fe713c07664df82a8d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/055/05559f0f2a69f1339ad3e9280dffe948acbf6112cdb0da23966cd8f5e97c7c99.mp3", "archive_relative_path": "raw/audio/055/05559f0f2a69f1339ad3e9280dffe948acbf6112cdb0da23966cd8f5e97c7c99.mp3" } ] } ], "prediction": "Amujpa, amujpa!", "reference": "Ge's'g, pe'l esgmali!" }, { "id": "mic-sent-d2366a24116d41ed06bfbdac:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My shirt is so old it's comming apart.", "output_text": "Tetujisa'qawei nugu' ntatla'im lpa sewisgiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My shirt is so old it's comming apart.", "mic_Latn": "Tetujisa'qawei nugu' ntatla'im lpa sewisgiet." }, "canonical_ref": "entries/s/sewisgiet/sewisgiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-339ab82524706809002d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sewisgiet/sewisgiet.html", "entry_url": "https://mikmaqonline.org/entries/s/sewisgiet/sewisgiet.html", "headword": "sewisgiet", "example_index": 0, "raw_html_path": "raw/entries/6e26a10d8ac92237014444b60300b51fb89726bf18893dac1a0ae6d4d614be54.html", "raw_html_sha256": "2594ec491e1560100cd6b8e08a3996a414dfc6ae9dcd0e61ef1d7a516c83f92c", "fetched_at": "2026-07-12T02:44:56.022Z", "recordings": [ { "recording_id": "979d3c7952809f6180942bb3536bd6800f995d39737bad82b7a70d52dca044b2", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b6f/b6fbe6c29c0a0984b8c92b01b495888405015434cf4e1ec614bca05b1a3987e5.mp3", "archive_relative_path": "raw/audio/b6f/b6fbe6c29c0a0984b8c92b01b495888405015434cf4e1ec614bca05b1a3987e5.mp3" } ] } ], "prediction": "Tetuji'j na ntus gisijig.", "reference": "Tetujisa'qawei nugu' ntatla'im lpa sewisgiet." }, { "id": "mic-sent-d2506d4c02b09e9c842dc13b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The cop stops the man on the road.", "output_text": "Gast'pl enqa'latl ji'nmul awtigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The cop stops the man on the road.", "mic_Latn": "Gast'pl enqa'latl ji'nmul awtigtug." }, "canonical_ref": "entries/e/enqa'latl/enqa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1dd3cdd371705e148a82", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/enqa'latl/enqa'latl.html", "entry_url": "https://mikmaqonline.org/entries/e/enqa'latl/enqa'latl.html", "headword": "enqa'latl", "example_index": 0, "raw_html_path": "raw/entries/3f79dabe0a8dc59b1e0756441592811109da67423bdb9ed4fedcddf716ea4519.html", "raw_html_sha256": "0b9371a890db95a0ad84a7b554b064da6d0b6394a1345929009ba2d6ee8bdca5", "fetched_at": "2026-07-12T02:38:05.506Z", "recordings": [ { "recording_id": "ad5800b38e788e52d9573163180fe83a01cdf7b23d85041ad22a0a0f0494f2ae", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ea8/ea8ad066777b6361bb687918000f8c237d52eac642503f0de430c8b0ea96e54f.mp3", "archive_relative_path": "raw/audio/ea8/ea8ad066777b6361bb687918000f8c237d52eac642503f0de430c8b0ea96e54f.mp3" } ] } ], "prediction": "Lpa'tu'ji'j gesatg ula ji'nm.", "reference": "Gast'pl enqa'latl ji'nmul awtigtug." }, { "id": "mic-sent-d25d5cd6690809d86a3f8067:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Joseph has so much money.", "output_text": "So'sep te'sung suliewei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Joseph has so much money.", "mic_Latn": "So'sep te'sung suliewei." }, "canonical_ref": "entries/t/te'sung/te'sung.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-668f97a148c1a7aca5d7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/te'sung/te'sung.html", "entry_url": "https://mikmaqonline.org/entries/t/te'sung/te'sung.html", "headword": "te'sung", "example_index": 0, "raw_html_path": "raw/entries/2742bb8f6bdfe8cfbf33687cce6d4a4c1406fd010f6872a5f4fbc5c4e88630c0.html", "raw_html_sha256": "246e5724b505357642e114c4979afd1c7118a71ce444a76f8fa1be7928a44421", "fetched_at": "2026-07-12T02:45:46.958Z", "recordings": [ { "recording_id": "4ad3e96bf50660176dcde7a13703da16bf11465e6b4dace0b7efb2d8a5ebce12", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ced/ced3e3117f93adfc5b9645bc28bd54d41832218be4e3a5e713b28ee7fcd607bd.mp3", "archive_relative_path": "raw/audio/ced/ced3e3117f93adfc5b9645bc28bd54d41832218be4e3a5e713b28ee7fcd607bd.mp3" } ] } ], "prediction": "So'sep ta'n te'sijig.", "reference": "So'sep te'sung suliewei." }, { "id": "mic-sent-d2f6319768dd09fe4d665219:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she got a painful burn, the poor thing!", "output_text": "Gesoqsit na ewuljewe'jit!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she got a painful burn, the poor thing!", "mic_Latn": "Gesoqsit na ewuljewe'jit!" }, "canonical_ref": "entries/g/gesoqsit/gesoqsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4e281f188039226bf7b0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesoqsit/gesoqsit.html", "entry_url": "https://mikmaqonline.org/entries/g/gesoqsit/gesoqsit.html", "headword": "gesoqsit", "example_index": 0, "raw_html_path": "raw/entries/99527bc989954600e7f1e4e7c0ec9b08c3660395d9c1eb0a45629e549b68b04e.html", "raw_html_sha256": "e5fbd6e9296991b5cc9abd42d275cd25db0a8fbed518c0a62988d0db3ddde73e", "fetched_at": "2026-07-12T02:39:17.772Z", "recordings": [ { "recording_id": "bbbc5b48e91da80533b0e8195405cd178fad08f9c92472855648929dcae2306c", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d7b/d7b546af08782753f7fc29ceb5abe3b4fdf72678803939e285a28cd0baa194aa.mp3", "archive_relative_path": "raw/audio/d7b/d7b546af08782753f7fc29ceb5abe3b4fdf72678803939e285a28cd0baa194aa.mp3" } ] } ], "prediction": "Pugwelg'g na we'gwi'g, lpa ji'nm!", "reference": "Gesoqsit na ewuljewe'jit!" }, { "id": "mic-sent-d306b01af5053cc3d4fa38f6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My son is going to request permission to marry their daughter tonight.", "output_text": "Ngwis to'q natgeluluet ulo'nug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My son is going to request permission to marry their daughter tonight.", "mic_Latn": "Ngwis to'q natgeluluet ulo'nug." }, "canonical_ref": "entries/g/geluluet/geluluet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b0d3ee0d6663e2db408e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/geluluet/geluluet.html", "entry_url": "https://mikmaqonline.org/entries/g/geluluet/geluluet.html", "headword": "geluluet", "example_index": 0, "raw_html_path": "raw/entries/a1e910327251fd47a999e5cd09f7948c158a4a5b792568d757f0751781a19bfd.html", "raw_html_sha256": "67e77311c2762b71fd727551b96e6b8c862099223ed528dec5e2ee6155da9feb", "fetched_at": "2026-07-12T02:38:57.279Z", "recordings": [ { "recording_id": "b5bac38067d7d92d060de98aaf9f22c0ee712e3fb4f0600552abc97d67495f7d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dba/dba1da460ad3d1b12db949f73dd4c3fd54c9dd7ce19b769b5c93b03cba4a2c69.mp3", "archive_relative_path": "raw/audio/dba/dba1da460ad3d1b12db949f73dd4c3fd54c9dd7ce19b769b5c93b03cba4a2c69.mp3" } ] } ], "prediction": "Ngwis e'pite's'g ugjit ugjit ula ji'nm gisgug.", "reference": "Ngwis to'q natgeluluet ulo'nug." }, { "id": "mic-sent-d3987e460c9224bb0fac6d0e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I'm going to pull down my shirt, I'm chilly.", "output_text": "Pe' nisega'l'g'p ula ntatlaim, gewjia'qiei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I'm going to pull down my shirt, I'm chilly.", "mic_Latn": "Pe' nisega'l'g'p ula ntatlaim, gewjia'qiei." }, "canonical_ref": "entries/n/nisega'latl/nisega'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-65a30db17b9b52cc4a30", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nisega'latl/nisega'latl.html", "entry_url": "https://mikmaqonline.org/entries/n/nisega'latl/nisega'latl.html", "headword": "nisega'latl", "example_index": 0, "raw_html_path": "raw/entries/c3965184977878a0a3b1a7cb091289fa7333b75b0475dd4f1deb32ed0af0cae5.html", "raw_html_sha256": "6fbf1f915cf648a6e936901692529873cef4fe3cd2b1a0d82b681fe9daa2405f", "fetched_at": "2026-07-12T02:42:36.530Z", "recordings": [ { "recording_id": "7e69e8082709c5976b3fed07f678dd6115342fb3fb3e78cee2202c8756516ede", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8e6/8e6199005df05a9785daeeb62206defc49016b4ff2ab508142d252b714c126d1.mp3", "archive_relative_path": "raw/audio/8e6/8e6199005df05a9785daeeb62206defc49016b4ff2ab508142d252b714c126d1.mp3" } ] } ], "prediction": "Nmu'j nugute'g ntmu'n, nige' negm.", "reference": "Pe' nisega'l'g'p ula ntatlaim, gewjia'qiei." }, { "id": "mic-sent-d3b1a04c663a37431d5aa107:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she pushed his/her car all the way to his/her house.", "output_text": "Lpa gesmoqja'toq utepaqan glapis wiguwaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she pushed his/her car all the way to his/her house.", "mic_Latn": "Lpa gesmoqja'toq utepaqan glapis wiguwaq." }, "canonical_ref": "entries/g/gesmoqja'toq/gesmoqja'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c2a09549a716dedc7ad2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesmoqja'toq/gesmoqja'toq.html", "entry_url": "https://mikmaqonline.org/entries/g/gesmoqja'toq/gesmoqja'toq.html", "headword": "gesmoqja'toq", "example_index": 0, "raw_html_path": "raw/entries/b9ad4b307450d750e79e4e0f36f96cfd3ffec4242716ff72a88b72eafcf3e5ec.html", "raw_html_sha256": "3248920aeacbf45d282c5bdc204ef256c204035bc42d822ac30ce39ee1638f91", "fetched_at": "2026-07-12T02:39:16.262Z", "recordings": [ { "recording_id": "74877d6ba4d0edadfbb580dcf53eb97bb01b209e448992c4dcc14790f76ba896", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/90f/90f876fef03c8fbc81e817907309f0512fe6d2a2449215ff709d92b50cf63f4b.mp3", "archive_relative_path": "raw/audio/90f/90f876fef03c8fbc81e817907309f0512fe6d2a2449215ff709d92b50cf63f4b.mp3" } ] } ], "prediction": "Te's'g na utepaqan ta'n tujiw ugjit ugjit.", "reference": "Lpa gesmoqja'toq utepaqan glapis wiguwaq." }, { "id": "mic-sent-d3b7f66657f4122bcdb68933:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Use the ones in the front first.", "output_text": "Ula nigantegl tmg e'we'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Use the ones in the front first.", "mic_Latn": "Ula nigantegl tmg e'we'n." }, "canonical_ref": "entries/n/niganteg/niganteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-53cadfbd6d51c9f48fde", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/niganteg/niganteg.html", "entry_url": "https://mikmaqonline.org/entries/n/niganteg/niganteg.html", "headword": "niganteg", "example_index": 0, "raw_html_path": "raw/entries/b2e132bfab989090515dae8cb83563006ebe9aa47a4ff0d0eb93b3ac39f1e62d.html", "raw_html_sha256": "1405ef6781b9c9bba110e2ed5fe120438e440c57e346399c3c939892e2002471", "fetched_at": "2026-07-12T02:42:31.295Z", "recordings": [ { "recording_id": "3bfd039be2e65c56ff1ab604110b4f417faae7712222c98dc29acf8d1fa9339d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/712/712652926d95d9c3572575356a055391e086889567558153e552d4c37d706f0e.mp3", "archive_relative_path": "raw/audio/712/712652926d95d9c3572575356a055391e086889567558153e552d4c37d706f0e.mp3" } ] } ], "prediction": "Amujpa ugt'p'ti'l ugjit.", "reference": "Ula nigantegl tmg e'we'n." }, { "id": "mic-sent-d3faa296ce5b9adbb45e6d7e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My aunt Mary, is from the south.", "output_text": "Nsugwis Mali, na tp'te'snugowi'sgw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My aunt Mary, is from the south.", "mic_Latn": "Nsugwis Mali, na tp'te'snugowi'sgw." }, "canonical_ref": "entries/t/tp'te'snugowi'sgw/tp'te'snugowi'sgw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-518a76ed6ef0cd0416c7", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tp'te'snugowi'sgw/tp'te'snugowi'sgw.html", "entry_url": "https://mikmaqonline.org/entries/t/tp'te'snugowi'sgw/tp'te'snugowi'sgw.html", "headword": "tp'te'snugowi'sgw", "example_index": 0, "raw_html_path": "raw/entries/be13981d7581f1619d2fa716874b5652d8a1247949e1d972a1e768dd3e1a109f.html", "raw_html_sha256": "7f199195ed25f83ee1ab3ea9d3f6c6924791ef28ddd405ef6aaa204f4eb06ac8", "fetched_at": "2026-07-12T02:46:06.063Z", "recordings": [ { "recording_id": "9ca01d358406ceeb6b345f856d5faf0a4445936879108f76192a1e92c535f897", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0aa/0aa5757f460ed6c04befb32d5f2e0ba096da312818a1cca7e41ab828e5fc3e6e.mp3", "archive_relative_path": "raw/audio/0aa/0aa5757f460ed6c04befb32d5f2e0ba096da312818a1cca7e41ab828e5fc3e6e.mp3" } ] } ], "prediction": "Mali nuji'j, na ji'nm.", "reference": "Nsugwis Mali, na tp'te'snugowi'sgw." }, { "id": "mic-sent-d402e05a24842f2517eb598c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My home is in front of the main street.", "output_text": "Ni'g nigantug eteg awtigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My home is in front of the main street.", "mic_Latn": "Ni'g nigantug eteg awtigtug." }, "canonical_ref": "entries/n/nigantug/nigantug.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d9303bd17b4521341e6e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nigantug/nigantug.html", "entry_url": "https://mikmaqonline.org/entries/n/nigantug/nigantug.html", "headword": "nigantug", "example_index": 0, "raw_html_path": "raw/entries/94067b302993812f421b8f2823327cddb46e652a477d67c6349f6e1f723ac585.html", "raw_html_sha256": "e5a708f09c77e07fdace02deb94f3a9c7b85641079fdcb2bb29480e5a0270b03", "fetched_at": "2026-07-12T02:42:31.511Z", "recordings": [ { "recording_id": "83b8f60d74f40ee058507090d3ca014af8b6c1475dbd057d4d9cf3b7318cede7", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/175/1758afc9c70be9cabd5c09d52fb5ff94b39bf3397e02f95e9609a51f48cc5880.mp3", "archive_relative_path": "raw/audio/175/1758afc9c70be9cabd5c09d52fb5ff94b39bf3397e02f95e9609a51f48cc5880.mp3" } ] } ], "prediction": "Ntus gisitu'g ugtaqanigtug.", "reference": "Ni'g nigantug eteg awtigtug." }, { "id": "mic-sent-d429b8be4b0ef103932b8d37:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There isn't much left of that fish, yet that cat is working hard to eat the scraps that are there.", "output_text": "Mu' nnim mesgilug esgwiet na nme'j, pas gatu gina'sit gajuewj matu'patl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There isn't much left of that fish, yet that cat is working hard to eat the scraps that are there.", "mic_Latn": "Mu' nnim mesgilug esgwiet na nme'j, pas gatu gina'sit gajuewj matu'patl." }, "canonical_ref": "entries/m/matu'patl/matu'patl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-17f79024c88e0cf36411", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/matu'patl/matu'patl.html", "entry_url": "https://mikmaqonline.org/entries/m/matu'patl/matu'patl.html", "headword": "matu'patl", "example_index": 0, "raw_html_path": "raw/entries/0a44415844836f543f3e2b20a0965eb79594acb6ae135718af9fdb607c30f32a.html", "raw_html_sha256": "371ca6e419b44a38ee35f1a2da812341bae193f2ec29655da0ef4ad416f9a840", "fetched_at": "2026-07-12T02:40:57.899Z", "recordings": [ { "recording_id": "aa72997a425d1fc84988781ffcdcd7fb613665000bcc52a1cd81f9e68990a8ec", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9c1/9c1fade34e1767c2bbafd4c40b9d564d54ade145ac32d050cbafcb37589b15f7.mp3", "archive_relative_path": "raw/audio/9c1/9c1fade34e1767c2bbafd4c40b9d564d54ade145ac32d050cbafcb37589b15f7.mp3" } ] } ], "prediction": "Mu' ms't te's'g na nuji'j, gatu na gajuewja'q na lpa gmu'j.", "reference": "Mu' nnim mesgilug esgwiet na nme'j, pas gatu gina'sit gajuewj matu'patl." }, { "id": "mic-sent-d435296a6a75d750e5d69652:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That person wearing mocassins, I like the beadwork on the mocassins.", "output_text": "Ala alma'gna'q, welaptmaqi ugma'gnmg ta'n telwaio'sgwa'tasinij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That person wearing mocassins, I like the beadwork on the mocassins.", "mic_Latn": "Ala alma'gna'q, welaptmaqi ugma'gnmg ta'n telwaio'sgwa'tasinij." }, "canonical_ref": "entries/m/ma'gna'q/ma'gna'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ee790ce2edb2206c9c65", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/ma'gna'q/ma'gna'q.html", "entry_url": "https://mikmaqonline.org/entries/m/ma'gna'q/ma'gna'q.html", "headword": "ma'gna'q", "example_index": 0, "raw_html_path": "raw/entries/52a2b2205709a148de0bcd87babc95c61f77ae545018077878055ff54e0c646c.html", "raw_html_sha256": "e9ac3fb479d8ee377152cb7b2491eaa29a7e2cae8d6f65136d370d925bfe2c25", "fetched_at": "2026-07-12T02:40:41.711Z", "recordings": [ { "recording_id": "a76cd2cd165f44457f68d01addeefc68ca5e93d5639edf653b8802e5c8bfe9ae", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ae3/ae37645e1406190d6361fef3d1e400796fc1a346cd678ebbd63fc08fda358a53.mp3", "archive_relative_path": "raw/audio/ae3/ae37645e1406190d6361fef3d1e400796fc1a346cd678ebbd63fc08fda358a53.mp3" } ] } ], "prediction": "Ala ji'nm gi's'g, nige' na gmu'j gisi'g.", "reference": "Ala alma'gna'q, welaptmaqi ugma'gnmg ta'n telwaio'sgwa'tasinij." }, { "id": "mic-sent-d4409780b9cd5adeaaa2e238:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There's a table facing towards here.", "output_text": "Ala' wejgwajeteg patawti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There's a table facing towards here.", "mic_Latn": "Ala' wejgwajeteg patawti." }, "canonical_ref": "entries/w/wejgwajeteg/wejgwajeteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7a7e431b2e9119cb5092", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wejgwajeteg/wejgwajeteg.html", "entry_url": "https://mikmaqonline.org/entries/w/wejgwajeteg/wejgwajeteg.html", "headword": "wejgwajeteg", "example_index": 0, "raw_html_path": "raw/entries/43bcfe80e7d0a0fdda3a95aac97ff0e12091091a73c95e90bc2aa154e8cf1d4f.html", "raw_html_sha256": "34d8e88e96c20d09e4a6048be9cc7f881f6e4e423f6fbd09253f0b7f710cfc3d", "fetched_at": "2026-07-12T02:46:49.983Z", "recordings": [ { "recording_id": "eba92435603a940ad70bea703498c88a4d1af6458a15d8a5bad9de5e52e455af", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/169/1697d85ce3236d7ab6670e0208bc6755271f2e5cd725fcfa68a5aecf64fc44c8.mp3", "archive_relative_path": "raw/audio/169/1697d85ce3236d7ab6670e0208bc6755271f2e5cd725fcfa68a5aecf64fc44c8.mp3" } ] } ], "prediction": "Ala ta'n te'sipow ula tet.", "reference": "Ala' wejgwajeteg patawti." }, { "id": "mic-sent-d4ad0b7ece87a1c0f7b03b9c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is going to pull and drag the little sled while it's slippery.", "output_text": "Wesuatejitoq na tepaqanji'j ge's welsesupe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is going to pull and drag the little sled while it's slippery.", "mic_Latn": "Wesuatejitoq na tepaqanji'j ge's welsesupe'g." }, "canonical_ref": "entries/w/wesuatejitoq/wesuatejitoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-75a9e31543f709b6bba2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wesuatejitoq/wesuatejitoq.html", "entry_url": "https://mikmaqonline.org/entries/w/wesuatejitoq/wesuatejitoq.html", "headword": "wesuatejitoq", "example_index": 0, "raw_html_path": "raw/entries/d63a534a5fe72196bdbf55c0be23e79c2dca108fd785a6f862504d88e004d8a1.html", "raw_html_sha256": "4360578df00fb113ff83ee862420cff5fe24a997334130a26501d1acb1238a5c", "fetched_at": "2026-07-12T02:47:21.670Z", "recordings": [ { "recording_id": "ea3007b3e3c8a4a2f103d351c50b15c33207ad73cf3dad7dc191a3c862d2b8cc", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9f6/9f64456e0ec0e9a79c842072f7b5ca0c19317af3d137dec2fd3a42245288eade.mp3", "archive_relative_path": "raw/audio/9f6/9f64456e0ec0e9a79c842072f7b5ca0c19317af3d137dec2fd3a42245288eade.mp3" } ] } ], "prediction": "Pugwelg aq gesatg na pi's'tji'ji'j ta'n tujiw gesgm'g.", "reference": "Wesuatejitoq na tepaqanji'j ge's welsesupe'g." }, { "id": "mic-sent-d56439a6e891bb5de4671711:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I had dental work done and I was given a needle, my mouth is still numb from it.", "output_text": "Nipitl elugwatmuimg'pnn aq sa'qatia'limg'p, me' newte' telpissagutnai.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I had dental work done and I was given a needle, my mouth is still numb from it.", "mic_Latn": "Nipitl elugwatmuimg'pnn aq sa'qatia'limg'p, me' newte' telpissagutnai." }, "canonical_ref": "entries/p/pissaqutnat/pissaqutnat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d20f35c504b5fe1ca949", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pissaqutnat/pissaqutnat.html", "entry_url": "https://mikmaqonline.org/entries/p/pissaqutnat/pissaqutnat.html", "headword": "pissaqutnat", "example_index": 0, "raw_html_path": "raw/entries/c72a614da264774bc02d25413cdc679baabbfeef4ec24948e7c73f1fb5ec025c.html", "raw_html_sha256": "fa0136e267e76c6fea6f44d9f75e07ca4d9deccd4629b8ee993907b3545c0a76", "fetched_at": "2026-07-12T02:44:04.767Z", "recordings": [ { "recording_id": "b4dc75e506a5d789062100d38913343d82bbaad1a08e73cdb0bfc90b4408766b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0e9/0e9fe0aab759e90e5c88a2cf2a7b359d434453b6c52c18d888bc1f58f86c7d73.mp3", "archive_relative_path": "raw/audio/0e9/0e9fe0aab759e90e5c88a2cf2a7b359d434453b6c52c18d888bc1f58f86c7d73.mp3" } ] } ], "prediction": "Amujpa'tuig aq gesgm'te'l, nige' na gmu'ji'j.", "reference": "Nipitl elugwatmuimg'pnn aq sa'qatia'limg'p, me' newte' telpissagutnai." }, { "id": "mic-sent-d56cbf80f4c5c4cce1b83924:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There are goats able to make their way on high steep terrain.", "output_text": "Eimu'tijig te'pljug gistesgmi'tij esp'saqteg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There are goats able to make their way on high steep terrain.", "mic_Latn": "Eimu'tijig te'pljug gistesgmi'tij esp'saqteg." }, "canonical_ref": "entries/e/esp'saqteg/esp'saqteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6469dc9ff78fd75d290d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/esp'saqteg/esp'saqteg.html", "entry_url": "https://mikmaqonline.org/entries/e/esp'saqteg/esp'saqteg.html", "headword": "esp'saqteg", "example_index": 0, "raw_html_path": "raw/entries/fcc0467d774fa813eb2e6c4a6049c1fa2f62749bc8b3c71e11124707e59d3af7.html", "raw_html_sha256": "088d3a7553fdd91c82be5d2bb12979adbb227573168784885ad4460d1faece94", "fetched_at": "2026-07-12T02:38:19.165Z", "recordings": [ { "recording_id": "63523e7e1b34fc953a9d87b64bd59ea8dfb7167119294fd2f4ea9da180652108", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6f8/6f8a4818e0548d7a46089e1196b4475b1120397cc061ae17e108d9d356a6e530.mp3", "archive_relative_path": "raw/audio/6f8/6f8a4818e0548d7a46089e1196b4475b1120397cc061ae17e108d9d356a6e530.mp3" } ] } ], "prediction": "Pugwelg'g na wi'gwi'g ta'n tujiw mesgijig.", "reference": "Eimu'tijig te'pljug gistesgmi'tij esp'saqteg." }, { "id": "mic-sent-d5c2cf812ce7724e4aebb869:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This water flows downstream, follow it and it'll take you where you want to go.", "output_text": "Ula samugwan papgitg, majulgwate'n aq la'lultew ta'n getu' lien.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This water flows downstream, follow it and it'll take you where you want to go.", "mic_Latn": "Ula samugwan papgitg, majulgwate'n aq la'lultew ta'n getu' lien." }, "canonical_ref": "entries/p/papgitg/papgitg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-75f042ed08fb74d91a0f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/papgitg/papgitg.html", "entry_url": "https://mikmaqonline.org/entries/p/papgitg/papgitg.html", "headword": "papgitg", "example_index": 0, "raw_html_path": "raw/entries/3842837e864322caa3faed8525e521133a77cd6ac60485b5247d4bfc41c3f53c.html", "raw_html_sha256": "7d911aca5c23f2391332cd4b0beab3128279a6ad91fd93bb6e87d470a377565d", "fetched_at": "2026-07-12T02:36:12.068Z", "recordings": [ { "recording_id": "b54e0a31727307335e53bdc9f703ed339ffc9c48c391ad91147cf757f00554d9", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3da/3daaa711eb7a97c831abc4ae617166b91572bac87444637f3a3b5d84d137401a.mp3", "archive_relative_path": "raw/audio/3da/3daaa711eb7a97c831abc4ae617166b91572bac87444637f3a3b5d84d137401a.mp3" } ] } ], "prediction": "Ula pemi'g etlugowa'q, glapis aq ta'n goqwei etltoqwei tujiw.", "reference": "Ula samugwan papgitg, majulgwate'n aq la'lultew ta'n getu' lien." }, { "id": "mic-sent-d62fef9bf804601b0d282669:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "As he/she opened, here he/she was looking at him/her!", "output_text": "Telpanta'toq ga'qan, u't ta wejgu'lapinitl!", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "As he/she opened, here he/she was looking at him/her!", "mic_Latn": "Telpanta'toq ga'qan, u't ta wejgu'lapinitl!" }, "canonical_ref": "entries/p/panta'toq/panta'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ba43538d9e2249a10b90", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/panta'toq/panta'toq.html", "entry_url": "https://mikmaqonline.org/entries/p/panta'toq/panta'toq.html", "headword": "panta'toq", "example_index": 0, "raw_html_path": "raw/entries/d6fe25852326196a5a90daaa7ee4ab21fd200c186bb86ac3142a909ef9874925.html", "raw_html_sha256": "d5e94212a604ebedb370fa4ea3a1c3681923bde18cd9b524330c7c1c2374d7be", "fetched_at": "2026-07-12T02:43:06.987Z", "recordings": [ { "recording_id": "a5fcc006ed7d8a772fb10f0333be9a6c2643afcf299b8b23338254a49c244096", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e98/e982afa80f778c8536435407a4d8a0b55688b7e0c869f9866707bb8d9f06ddd0.mp3", "archive_relative_path": "raw/audio/e98/e982afa80f778c8536435407a4d8a0b55688b7e0c869f9866707bb8d9f06ddd0.mp3" } ] } ], "prediction": "Ge's gesatg, ula tet etl'g'p!", "reference": "Telpanta'toq ga'qan, u't ta wejgu'lapinitl!" }, { "id": "mic-sent-d65818f92d48e0ec1056ca7f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I accidentally burned myself this morning.", "output_text": "Gispejigaqsusi sepei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I accidentally burned myself this morning.", "mic_Latn": "Gispejigaqsusi sepei." }, "canonical_ref": "entries/g/gaqsusit/gaqsusit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7ebcf3363271f3b29d39", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gaqsusit/gaqsusit.html", "entry_url": "https://mikmaqonline.org/entries/g/gaqsusit/gaqsusit.html", "headword": "gaqsusit", "example_index": 0, "raw_html_path": "raw/entries/8bf4c1e82791aa982853dc5bfdc36524d0fe5d059f30a74d368280991b546422.html", "raw_html_sha256": "15bc25a4588cfd9edb546969bc4b4200f025f6901753203fee455a5033705e7a", "fetched_at": "2026-07-12T02:38:42.514Z", "recordings": [ { "recording_id": "0247bfaa5774da430e543345475ed65c53b7c22bab0a36201f636a466b666209", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9c7/9c7ca3ad9769546d5ba76a4119c9e6f0c90b9dda20d80f3cb5dd551909ddbd97.mp3", "archive_relative_path": "raw/audio/9c7/9c7ca3ad9769546d5ba76a4119c9e6f0c90b9dda20d80f3cb5dd551909ddbd97.mp3" } ] } ], "prediction": "Pugwelg'g ula egsitpu'g.", "reference": "Gispejigaqsusi sepei." }, { "id": "mic-sent-d66bbf10ba6ea523c69aea16:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My daughter comes in and my dog comes in with her.", "output_text": "Ntus pisgwa't aq nti pisguije'watl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My daughter comes in and my dog comes in with her.", "mic_Latn": "Ntus pisgwa't aq nti pisguije'watl." }, "canonical_ref": "entries/p/pisguije'watl/pisguije'watl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c34c6c1d0d90381071dc", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pisguije'watl/pisguije'watl.html", "entry_url": "https://mikmaqonline.org/entries/p/pisguije'watl/pisguije'watl.html", "headword": "pisguije'watl", "example_index": 0, "raw_html_path": "raw/entries/8afc3740e41ae5c3ba0e05a6f953707b9e38940249b1349a8b33b2266f6e351a.html", "raw_html_sha256": "39577fcdee9b97d5e62479e7ef1a8625f4b95333b0a59f021b9f2b235fbe9af6", "fetched_at": "2026-07-12T02:44:02.357Z", "recordings": [ { "recording_id": "ec316f00b9de3ea5c3efe0db173e666c669c5f1addebe48dbd75d9c6e201fbc0", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e24/e2408546fc1c2c2739b7e6cff1b8f88c22808c01a5706079f1a5d81aa6acf030.mp3", "archive_relative_path": "raw/audio/e24/e2408546fc1c2c2739b7e6cff1b8f88c22808c01a5706079f1a5d81aa6acf030.mp3" } ] } ], "prediction": "Ntus e'pit aq nti e'pitew.", "reference": "Ntus pisgwa't aq nti pisguije'watl." }, { "id": "mic-sent-d70cc9f10676f5172fa44c0b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That's my dress.", "output_text": "Ni'newei na magot.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That's my dress.", "mic_Latn": "Ni'newei na magot." }, "canonical_ref": "entries/n/ni'newei/ni'newei.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e5e4c61f0d9566f9bec2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/ni'newei/ni'newei.html", "entry_url": "https://mikmaqonline.org/entries/n/ni'newei/ni'newei.html", "headword": "ni'newei", "example_index": 1, "raw_html_path": "raw/entries/5e7855fd061af2c580bb54b4cda462a02304e906481570685ad2c65962d388d2.html", "raw_html_sha256": "810ee412626af199bbb68ebf5f9f7cd7ae0761cc8ef23f055e2ca33ebb1d100a", "fetched_at": "2026-07-12T02:42:34.421Z", "recordings": [ { "recording_id": "b2f3d9fd33d06d379d2a54e1353160c3c80d2f7483d636f3db146e50a1a19e46", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/444/444bdac79475545027ce7bbabc5a588d9de81617169cfac71b7d60dad0633f63.mp3", "archive_relative_path": "raw/audio/444/444bdac79475545027ce7bbabc5a588d9de81617169cfac71b7d60dad0633f63.mp3" } ] } ], "prediction": "Ala na nt'g.", "reference": "Ni'newei na magot." }, { "id": "mic-sent-d70ffd5f6b7cfbc0dae48d6d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she knows how to stretch things, including the truth.", "output_text": "(N)atawisiptaqa'toq goqwei, we'gaw teliaqewei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she knows how to stretch things, including the truth.", "mic_Latn": "(N)atawisiptaqa'toq goqwei, we'gaw teliaqewei." }, "canonical_ref": "entries/s/siptaqa'toq/siptaqa'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3b1843335613a224edbb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/siptaqa'toq/siptaqa'toq.html", "entry_url": "https://mikmaqonline.org/entries/s/siptaqa'toq/siptaqa'toq.html", "headword": "siptaqa'toq", "example_index": 0, "raw_html_path": "raw/entries/1b46d86a3ce4fba57c01b647a3b702ad62eec677aa6d03d8a198a537f3375cef.html", "raw_html_sha256": "44aa1ea7474c562d80d23668d187a0bc367cb650a9f84c4430982980b906a896", "fetched_at": "2026-07-12T02:45:06.876Z", "recordings": [ { "recording_id": "0fa596fa695fb0bdc6b1ad31916af5ed531ba3cce81f87d00233c9eb3a5923b3", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d28/d2894df20c6018afe624de1c17095dc02e1aecb62985ba04a76c688f46f29cd6.mp3", "archive_relative_path": "raw/audio/d28/d2894df20c6018afe624de1c17095dc02e1aecb62985ba04a76c688f46f29cd6.mp3" } ] } ], "prediction": "Amujpa ta'n tujiw gisijig, te's goqwei wi'g.", "reference": "(N)atawisiptaqa'toq goqwei, we'gaw teliaqewei." }, { "id": "mic-sent-d820cef17f2769e538672ed5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The siblings are both soldiers.", "output_text": "Wijig'tijig gitg sma'gnisuijig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The siblings are both soldiers.", "mic_Latn": "Wijig'tijig gitg sma'gnisuijig." }, "canonical_ref": "entries/s/sma'gnisuit/sma'gnisuit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9cc73651c85bbf5bf3d5", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sma'gnisuit/sma'gnisuit.html", "entry_url": "https://mikmaqonline.org/entries/s/sma'gnisuit/sma'gnisuit.html", "headword": "sma'gnisuit", "example_index": 0, "raw_html_path": "raw/entries/32732570a1ccc8df8810debe03086777269343e05491d1ed1d24db98337fc7cd.html", "raw_html_sha256": "ed905151384dd21851e7da855f5f106f46a2b7f4a91cd719e9b1b96247360293", "fetched_at": "2026-07-12T02:45:11.915Z", "recordings": [ { "recording_id": "cb6082adfb52a57e01c3f8fc15d2db5d212672f45b03f80edd39e94c8191705f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/495/4958379fbb5b9b7aa3cd6432c211d316128989345b994672136663c493b6702e.mp3", "archive_relative_path": "raw/audio/495/4958379fbb5b9b7aa3cd6432c211d316128989345b994672136663c493b6702e.mp3" } ] } ], "prediction": "Amujpa'ji'jig na we'gwi'gig.", "reference": "Wijig'tijig gitg sma'gnisuijig." }, { "id": "mic-sent-d8dbd38fca3d627be917d496:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she accidently bumped his/her kid brother.", "output_text": "Ugjignaml gis'pettesguatl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she accidently bumped his/her kid brother.", "mic_Latn": "Ugjignaml gis'pettesguatl." }, "canonical_ref": "entries/p/pettesguatl/pettesguatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6eb50afd80f807e673ba", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pettesguatl/pettesguatl.html", "entry_url": "https://mikmaqonline.org/entries/p/pettesguatl/pettesguatl.html", "headword": "pettesguatl", "example_index": 0, "raw_html_path": "raw/entries/ba5822d4a3798c068057b162b1396bdb45c95e257d9ceb061b4634fca706ed14.html", "raw_html_sha256": "4a1a3eaa32c42a1670934b55457f97226f4fe7b01f15ba02b153ea903c37b943", "fetched_at": "2026-07-12T02:43:49.504Z", "recordings": [ { "recording_id": "f5291dc59bb83b8790f093ec0a5b40b75e47a8d47413d7d9856a026658a384fe", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/89a/89aad44c9c289f2e2c12afb50f243b281b18e230b8022b82b347ddaa749f8f2e.mp3", "archive_relative_path": "raw/audio/89a/89aad44c9c289f2e2c12afb50f243b281b18e230b8022b82b347ddaa749f8f2e.mp3" } ] } ], "prediction": "Gesatg ugji'jl ugjitl.", "reference": "Ugjignaml gis'pettesguatl." }, { "id": "mic-sent-d8f18fa0c0c88a6193b05da3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is crouching near a tree, he/she is waiting for a moose.", "output_text": "Gigji'w miti'sigtug mesqanepit, esgipa'tl tia'mul.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is crouching near a tree, he/she is waiting for a moose.", "mic_Latn": "Gigji'w miti'sigtug mesqanepit, esgipa'tl tia'mul." }, "canonical_ref": "entries/m/mesqanepit/mesqanepit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5853f2266bfca39e4ee6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mesqanepit/mesqanepit.html", "entry_url": "https://mikmaqonline.org/entries/m/mesqanepit/mesqanepit.html", "headword": "mesqanepit", "example_index": 0, "raw_html_path": "raw/entries/faabfe41971f8228ff49f28d706f56cf6ce9e7733cea81509bd5caea1445f8b9.html", "raw_html_sha256": "8a1f0449f2c968598d32534ca15b0ea249d5b7920ed05682e59b4aba54529051", "fetched_at": "2026-07-12T02:41:23.239Z", "recordings": [ { "recording_id": "8097f5fba48f28e312517fcc31ea381f3f20fb49f7584c5eac3aa0f117845a47", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d03/d03f179963fcf97c02446f359a742798566072b6e374f93e2494842c129db993.mp3", "archive_relative_path": "raw/audio/d03/d03f179963fcf97c02446f359a742798566072b6e374f93e2494842c129db993.mp3" } ] } ], "prediction": "Pugwelg witap, etl'gwatg ugjit.", "reference": "Gigji'w miti'sigtug mesqanepit, esgipa'tl tia'mul." }, { "id": "mic-sent-d91be909e808e13642567adf:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This woman is very short.", "output_text": "Gesitowaqji'jit na ula e'pit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This woman is very short.", "mic_Latn": "Gesitowaqji'jit na ula e'pit." }, "canonical_ref": "entries/g/gesitowaqji'jit/gesitowaqji'jit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-945e0f96b9a78280e3a8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesitowaqji'jit/gesitowaqji'jit.html", "entry_url": "https://mikmaqonline.org/entries/g/gesitowaqji'jit/gesitowaqji'jit.html", "headword": "gesitowaqji'jit", "example_index": 0, "raw_html_path": "raw/entries/a6f918842a9f335a166d09c7ac3a5a0a1d651e2879e22fe5749de54f7208c41d.html", "raw_html_sha256": "0999be34b6a00b17a66b142531c2d71c434b025019e277a6b57973ba40314b0e", "fetched_at": "2026-07-12T02:39:14.944Z", "recordings": [ { "recording_id": "bb09b26a29d6b01c75126044a30293c4468f1d2979bf4d946d996ff4a9f4acb1", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/399/399b9e839ebb4e0fa6eb7a5e6b6a283b0cdcd28e6015652b8b2da45334013b30.mp3", "archive_relative_path": "raw/audio/399/399b9e839ebb4e0fa6eb7a5e6b6a283b0cdcd28e6015652b8b2da45334013b30.mp3" } ] } ], "prediction": "Ula ji'nm na mawji'jg.", "reference": "Gesitowaqji'jit na ula e'pit." }, { "id": "mic-sent-d9702a8cb79718125aa06c15:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "See that person over there about to sit down, that is the one you want to speak to.", "output_text": "Ala nemi't pempa'sit, na negm getu'glult.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "See that person over there about to sit down, that is the one you want to speak to.", "mic_Latn": "Ala nemi't pempa'sit, na negm getu'glult." }, "canonical_ref": "entries/p/pempa'sit/pempa'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e0dbdddb828612314d56", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pempa'sit/pempa'sit.html", "entry_url": "https://mikmaqonline.org/entries/p/pempa'sit/pempa'sit.html", "headword": "pempa'sit", "example_index": 0, "raw_html_path": "raw/entries/6600581faa645c28e33912b538e38beda87096786a0be503b734ae3160d5ffab.html", "raw_html_sha256": "75f562bd0377385972d12b21bb883d7873aed23e384d6c20a3be528226136cb6", "fetched_at": "2026-07-12T02:43:35.637Z", "recordings": [ { "recording_id": "6eddc6d14a7b3433b0191e35eb15c1c72a40352476402afac8f69a81e7d00731", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3b8/3b858781a420253048020ffb482a04ad92c6bba0a8d0ee1209e500730465f130.mp3", "archive_relative_path": "raw/audio/3b8/3b858781a420253048020ffb482a04ad92c6bba0a8d0ee1209e500730465f130.mp3" } ] } ], "prediction": "Ge' jugwa'toq na ji'nm, na ta'n tujiw getu' gisiw.", "reference": "Ala nemi't pempa'sit, na negm getu'glult." }, { "id": "mic-sent-d9f42ad8c1da2c1c5820f264:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary understands the Mi'gmaq language.", "output_text": "Mali' nest'g Mi'gmewei tli'suti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary understands the Mi'gmaq language.", "mic_Latn": "Mali' nest'g Mi'gmewei tli'suti." }, "canonical_ref": "entries/n/nest'g/nest'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4006bcce1fe7f596cb42", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nest'g/nest'g.html", "entry_url": "https://mikmaqonline.org/entries/n/nest'g/nest'g.html", "headword": "nest'g", "example_index": 0, "raw_html_path": "raw/entries/3d97b7ee1d0225041e4617174b5e16f260b3446d223adc8d210446fc766cd215.html", "raw_html_sha256": "288c331914eee956c1dd672311eab378cab5f9a0531bfdc9386addfe61d91ae0", "fetched_at": "2026-07-12T02:42:23.450Z", "recordings": [ { "recording_id": "48fc606b7dc1ea4813c57f94ac59cb8e3f63a9296ffa8b997e46385cc18c0131", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/170/170995b2cb007721bb4201cd4188e00517be88eaa718f4f0ffb6685e4f48fb48.mp3", "archive_relative_path": "raw/audio/170/170995b2cb007721bb4201cd4188e00517be88eaa718f4f0ffb6685e4f48fb48.mp3" } ] } ], "prediction": "Mali gi's na Mi'gme'g.", "reference": "Mali' nest'g Mi'gmewei tli'suti." }, { "id": "mic-sent-da33bb4d43962f4a80225f4d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has been sitting on his/her foot for a long time, now it feels like pins and needles.", "output_text": "Sa'q uggwat pasg'g, nige' sa'qati'ju'aq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has been sitting on his/her foot for a long time, now it feels like pins and needles.", "mic_Latn": "Sa'q uggwat pasg'g, nige' sa'qati'ju'aq." }, "canonical_ref": "entries/p/pasg'g/pasg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e843112d08f21294dd39", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pasg'g/pasg'g.html", "entry_url": "https://mikmaqonline.org/entries/p/pasg'g/pasg'g.html", "headword": "pasg'g", "example_index": 0, "raw_html_path": "raw/entries/1d4d4958a70533278d61b48d3e829346c80101d97a18db4f0c53a28274560d6b.html", "raw_html_sha256": "a398b9e53dd35c8b118c7464dc3633aa6786ecf82c30281cd643f719ceee9ca0", "fetched_at": "2026-07-12T02:43:13.808Z", "recordings": [ { "recording_id": "a1b5fd9551572471ac6a67ad51c9bbbdcd72625269092948d12ec40111db4514", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fa2/fa21afa38677b5528a5397ea481895e34fceb93aa20ce252ea8ca5afcf3dc150.mp3", "archive_relative_path": "raw/audio/fa2/fa21afa38677b5528a5397ea481895e34fceb93aa20ce252ea8ca5afcf3dc150.mp3" } ] } ], "prediction": "Gi's gi's gaqa'latl, nige' negm na gmu'j.", "reference": "Sa'q uggwat pasg'g, nige' sa'qati'ju'aq." }, { "id": "mic-sent-da54235b827e65f9d55acab4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I think it's not narrow enough.", "output_text": "Telte'tm nutqwijijigwe'jg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I think it's not narrow enough.", "mic_Latn": "Telte'tm nutqwijijigwe'jg." }, "canonical_ref": "entries/n/nutqwijijigwe'jg/nutqwijijigwe'jg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-724b23914422da505b36", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nutqwijijigwe'jg/nutqwijijigwe'jg.html", "entry_url": "https://mikmaqonline.org/entries/n/nutqwijijigwe'jg/nutqwijijigwe'jg.html", "headword": "nutqwijijigwe'jg", "example_index": 0, "raw_html_path": "raw/entries/ecadcef58f2695dca5b7afe53274b3fd6194a4ac144f01fac7dac0dd65f3ca17.html", "raw_html_sha256": "336b7a4b23315b15892aff0641d4ce1cb27dd558a03ef26eb1807a8c07640e9a", "fetched_at": "2026-07-12T02:42:58.546Z", "recordings": [ { "recording_id": "5348414d075b558207775ed7945cd22f2c163ba24d20fb1a01b06a5e6608dedc", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4fd/4fd7dd6f2746981fffa120785744e9be0e69bc4ea76c53fd2162bed97f23fc13.mp3", "archive_relative_path": "raw/audio/4fd/4fd7dd6f2746981fffa120785744e9be0e69bc4ea76c53fd2162bed97f23fc13.mp3" } ] } ], "prediction": "Telte'lmu'j mu gesatg.", "reference": "Telte'tm nutqwijijigwe'jg." }, { "id": "mic-sent-da6112da214812d6a3fa5daa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she who molests is a dog.", "output_text": "Nmu'juit ta'n wen sespo'teget.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she who molests is a dog.", "mic_Latn": "Nmu'juit ta'n wen sespo'teget." }, "canonical_ref": "entries/s/sespo'teget/sespo'teget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0565d3648a7cf973dab0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sespo'teget/sespo'teget.html", "entry_url": "https://mikmaqonline.org/entries/s/sespo'teget/sespo'teget.html", "headword": "sespo'teget", "example_index": 0, "raw_html_path": "raw/entries/1d7e01b88287a56bf8f513e556eaaf16c290f78218fa6125689279f20a451d0b.html", "raw_html_sha256": "90da0262fc08e5d80009b5fbe5783ef94fc58c400da7d0bdecda0481836eecb5", "fetched_at": "2026-07-12T02:44:53.830Z", "recordings": [ { "recording_id": "22effd740a34c120ef1fcd599c0c731837d5b4864677e0ae40daa32cbb2ab3eb", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/95f/95fb9979e073cdb262d8f105865beb03e9d47ee3756a2ca0ecab6d87cec71676.mp3", "archive_relative_path": "raw/audio/95f/95fb9979e073cdb262d8f105865beb03e9d47ee3756a2ca0ecab6d87cec71676.mp3" } ] } ], "prediction": "Nmu'ji'j ta'n tujiw nmu'j.", "reference": "Nmu'juit ta'n wen sespo'teget." }, { "id": "mic-sent-daeb03e8787579d568f06569:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Each time I see Patrick he's running along, he must like running around.", "output_text": "Te's nemi'g Pa'tlig na pemi'pit, etna amuj gsatmutug ali'pij.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Each time I see Patrick he's running along, he must like running around.", "mic_Latn": "Te's nemi'g Pa'tlig na pemi'pit, etna amuj gsatmutug ali'pij." }, "canonical_ref": "entries/p/pemi'pit/pemi'pit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-849009c1414eb51f23a3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemi'pit/pemi'pit.html", "entry_url": "https://mikmaqonline.org/entries/p/pemi'pit/pemi'pit.html", "headword": "pemi'pit", "example_index": 0, "raw_html_path": "raw/entries/1eb9b9de37cd133c915ca3115a48839f82c5be929577342b469fe2c26e849ea5.html", "raw_html_sha256": "ea4af0a4e208d4dcb2e6ecc812e2ea0ee192fe7c9f18b86c4f39156ffe44ce4a", "fetched_at": "2026-07-12T02:43:32.501Z", "recordings": [ { "recording_id": "35b8bc0fd128baaa7fe3ef06cda3b2a2594bf84dd28b847956e1172510e73727", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7b7/7b7ab01c90acafe4617e3b0a126681bde4be729e7aed2fc75a5b91c4ee70c831.mp3", "archive_relative_path": "raw/audio/7b7/7b7ab01c90acafe4617e3b0a126681bde4be729e7aed2fc75a5b91c4ee70c831.mp3" } ] } ], "prediction": "Te's nige' nemi'g Patli'l gesatg, amujpa mesatg wesatg.", "reference": "Te's nemi'g Pa'tlig na pemi'pit, etna amuj gsatmutug ali'pij." }, { "id": "mic-sent-dbe51afc3d1a50ff8da9ab78:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little boy looked very surprised, when he saw a moose for the first time.", "output_text": "We'gwipa'qala'ig lpa'tuji'j, amgwes nemiatl tia'mul.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little boy looked very surprised, when he saw a moose for the first time.", "mic_Latn": "We'gwipa'qala'ig lpa'tuji'j, amgwes nemiatl tia'mul." }, "canonical_ref": "entries/n/nemiatl/nemiatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-b04ef0bd39007ec6087d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nemiatl/nemiatl.html", "entry_url": "https://mikmaqonline.org/entries/n/nemiatl/nemiatl.html", "headword": "nemiatl", "example_index": 0, "raw_html_path": "raw/entries/21d9f8d1d3f00b42820c6d03dc71543d2667a5e594c2cc292e9745d5d9cdf6a4.html", "raw_html_sha256": "4639f4364f670c8b372acae7919dc80dff25558a658e0e70ae87b87f3dba4ee6", "fetched_at": "2026-07-12T02:42:17.824Z", "recordings": [ { "recording_id": "07e6bb23705528942e6690fc6546553e30fe5b09f0f413848bdf16c26185f87f", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4e5/4e548c7cacb1e8ea70ae943c56a6971e66bee9e85bf91c3876a847f0fd7e2187.mp3", "archive_relative_path": "raw/audio/4e5/4e548c7cacb1e8ea70ae943c56a6971e66bee9e85bf91c3876a847f0fd7e2187.mp3" } ] } ], "prediction": "Lpa'tu'ji'j gesatg, ta'n tujiw na'te'l.", "reference": "We'gwipa'qala'ig lpa'tuji'j, amgwes nemiatl tia'mul." }, { "id": "mic-sent-dbe73686458b344cabd8190a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Marrow bons is excellent as medicine.", "output_text": "Wi'nei waqantew na mawglu'lg ugjit npisun.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Marrow bons is excellent as medicine.", "mic_Latn": "Wi'nei waqantew na mawglu'lg ugjit npisun." }, "canonical_ref": "entries/w/wi'nei_waqantew/wi'nei_waqantew.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-05757bf79e2d0cbae740", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wi'nei_waqantew/wi'nei_waqantew.html", "entry_url": "https://mikmaqonline.org/entries/w/wi'nei_waqantew/wi'nei_waqantew.html", "headword": "wi'nei_waqantew", "example_index": 0, "raw_html_path": "raw/entries/011930b90ed1fd7d04c0374c57cf8423435b271ea6278c3da191d6947027dde9.html", "raw_html_sha256": "4751833b8e558c7ec376d6c3625a3b766f25aaa7a9711bec6c5db75d296dce09", "fetched_at": "2026-07-12T02:47:34.930Z", "recordings": [ { "recording_id": "61f5033e425f4f00c60b7089567f2a2200e9956b6746209aa09d6d7ec43ae67f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/61d/61d37d4ec10e2bd39b7a358eeffaf89aac53760f7966273ba98683ae37757c51.mp3", "archive_relative_path": "raw/audio/61d/61d37d4ec10e2bd39b7a358eeffaf89aac53760f7966273ba98683ae37757c51.mp3" } ] } ], "prediction": "Me'gwi'g na we'gwig ta'n tujiw ugjit.", "reference": "Wi'nei waqantew na mawglu'lg ugjit npisun." }, { "id": "mic-sent-dc198646bf5db3c3dee722e0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where is your boat anchored?", "output_text": "Tami egumig utul?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where is your boat anchored?", "mic_Latn": "Tami egumig utul?" }, "canonical_ref": "entries/e/egumig/egumig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9b59104be0509172b51d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/egumig/egumig.html", "entry_url": "https://mikmaqonline.org/entries/e/egumig/egumig.html", "headword": "egumig", "example_index": 0, "raw_html_path": "raw/entries/49118b842238ed5df6c68e36d666f546d0487a9228a4b7b9f4e0d3868dfabb36.html", "raw_html_sha256": "8c1583d55f37d8167747bc4a919b457e3cdf4be85fbc54b1bb8c2021c1b01a46", "fetched_at": "2026-07-12T02:37:31.901Z", "recordings": [ { "recording_id": "56527dbd622a1ccb5d06bb39a1045f3c8ff63d541dcdf46e76e5cca9b8bbaf34", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/220/2201ab560bc23525727b32c1c875e45996ec10bbc7baf819dfefc71e8bc4df02.mp3", "archive_relative_path": "raw/audio/220/2201ab560bc23525727b32c1c875e45996ec10bbc7baf819dfefc71e8bc4df02.mp3" } ] } ], "prediction": "Tami gesatg na utepaqan?", "reference": "Tami egumig utul?" }, { "id": "mic-sent-dc2ac20cf82e5aac3b380590:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Stairs are necessary for a two storey house.", "output_text": "Lgusuaqann amujpa iga'tas'gl tapu eli'ganig wenji'guom.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Stairs are necessary for a two storey house.", "mic_Latn": "Lgusuaqann amujpa iga'tas'gl tapu eli'ganig wenji'guom." }, "canonical_ref": "entries/l/lgusuaqan/lgusuaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8e06e4ad1c45fbdfaf05", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lgusuaqan/lgusuaqan.html", "entry_url": "https://mikmaqonline.org/entries/l/lgusuaqan/lgusuaqan.html", "headword": "lgusuaqan", "example_index": 0, "raw_html_path": "raw/entries/7dc9049b60e2c3bc01b73fc54ebeb22a12f8b056fde0379773a55a40c1fff158.html", "raw_html_sha256": "ff2f987c924ac6b66a9959a50acf9f260e32a2e821d8524b007f6d15c42c17ba", "fetched_at": "2026-07-12T02:40:34.394Z", "recordings": [ { "recording_id": "054b1eb4cad1becd605848e74b58bb24c1fe2c0807b204fb38a36762e7ea2e8b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/7fb/7fbcecc86c285e821f4dfc987db2a145921fe4e5332f02fe4a924bd47428b091.mp3", "archive_relative_path": "raw/audio/7fb/7fbcecc86c285e821f4dfc987db2a145921fe4e5332f02fe4a924bd47428b091.mp3" } ] } ], "prediction": "Amujpa ms't wenji'guomg ta'n tujiw gaqapijig.", "reference": "Lgusuaqann amujpa iga'tas'gl tapu eli'ganig wenji'guom." }, { "id": "mic-sent-dc3444dfd4dd2ccb705ec185:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she walked all morning, now he/she is tiring.", "output_text": "Newtiegsitpu'g atl'get, nige' gispniet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she walked all morning, now he/she is tiring.", "mic_Latn": "Newtiegsitpu'g atl'get, nige' gispniet." }, "canonical_ref": "entries/g/gispniet/gispniet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9550158d99072bc7f4a0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gispniet/gispniet.html", "entry_url": "https://mikmaqonline.org/entries/g/gispniet/gispniet.html", "headword": "gispniet", "example_index": 0, "raw_html_path": "raw/entries/01d8877283122c09dc1266b86298638280f804897081938bc8fc309a6c54fd2b.html", "raw_html_sha256": "6db412db5c1420fd5c1d940ac74ce0aca392307cacbad27b1ab8c6109f712bc7", "fetched_at": "2026-07-12T02:39:42.792Z", "recordings": [ { "recording_id": "a96a4699c7e66c7493147345389a0fadae675720492c929590ff7c2efcff1c6f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/346/346df6f9f403a079de30e998dafc717e9ba51cdb7215ac98171c6badcc764a38.mp3", "archive_relative_path": "raw/audio/346/346df6f9f403a079de30e998dafc717e9ba51cdb7215ac98171c6badcc764a38.mp3" } ] } ], "prediction": "Newte'pugsitpu'g, nige' gesatg.", "reference": "Newtiegsitpu'g atl'get, nige' gispniet." }, { "id": "mic-sent-dd303bf4bafe356a51d9a50a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she thinks more highly of his/her car than he/she does of me.", "output_text": "Je me' megite'tg na utepaqan aq ni'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she thinks more highly of his/her car than he/she does of me.", "mic_Latn": "Je me' megite'tg na utepaqan aq ni'n." }, "canonical_ref": "entries/m/megite'tg/megite'tg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5bb10dd67e4185a460c9", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/megite'tg/megite'tg.html", "entry_url": "https://mikmaqonline.org/entries/m/megite'tg/megite'tg.html", "headword": "megite'tg", "example_index": 0, "raw_html_path": "raw/entries/0abed9ab1db8e14dfef03e667123bc11685cd9dc82297a44016cec4b37c8e632.html", "raw_html_sha256": "cfb9b422aa0556a7617b5ec32da7315428b2ebf188bbcd1a427679ca1cc3cef1", "fetched_at": "2026-07-12T02:41:07.144Z", "recordings": [ { "recording_id": "bec39859b6a3a5bb12748436a03822330faf78804a2d64f303bacf2684a3f118", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/433/433a6db43e3b0f7839ea022f79804537901f525df5c97b69406b66978a9e2250.mp3", "archive_relative_path": "raw/audio/433/433a6db43e3b0f7839ea022f79804537901f525df5c97b69406b66978a9e2250.mp3" } ] } ], "prediction": "Me' gesatg na utepaqan ugjit me' nige' ni'n.", "reference": "Je me' megite'tg na utepaqan aq ni'n." }, { "id": "mic-sent-dd75c83093b043e74e87a2c5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Let me just look over this picture.", "output_text": "Pe' ilamg'p ula napui'gign.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Let me just look over this picture.", "mic_Latn": "Pe' ilamg'p ula napui'gign." }, "canonical_ref": "entries/i/ilamatl/ilamatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ff73a05255e1f5454c90", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/ilamatl/ilamatl.html", "entry_url": "https://mikmaqonline.org/entries/i/ilamatl/ilamatl.html", "headword": "ilamatl", "example_index": 0, "raw_html_path": "raw/entries/d53846a729aff70b78300557459d633739dd17e5e4d6860ee34dd764360b74ef.html", "raw_html_sha256": "44a9bf7781dd54997e71cb557ebda07975e68c784f1cbe74ec4902d1036b23d1", "fetched_at": "2026-07-12T02:40:06.645Z", "recordings": [ { "recording_id": "9f4fbfc7c95c0749ef8a67dc418af8cb77ccc46fc6f345a7a967977741a6cb1f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/dd2/dd2182a0b89b114f079f3aafcc4269562f94121ef1e596dde6a4e7505081103a.mp3", "archive_relative_path": "raw/audio/dd2/dd2182a0b89b114f079f3aafcc4269562f94121ef1e596dde6a4e7505081103a.mp3" } ] } ], "prediction": "Ge' negm gi'l na ula pilei.", "reference": "Pe' ilamg'p ula napui'gign." }, { "id": "mic-sent-de599e0567ce01031568e28b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It is only five o'clock and it is getting dark already.", "output_text": "Pas'g na'n ajiet aq gi's oqonitpaqamugwiaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It is only five o'clock and it is getting dark already.", "mic_Latn": "Pas'g na'n ajiet aq gi's oqonitpaqamugwiaq." }, "canonical_ref": "entries/o/oqonitpaqamugwiaq/oqonitpaqamugwiaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-36e1ff58a0c156c0ab45", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/o/oqonitpaqamugwiaq/oqonitpaqamugwiaq.html", "entry_url": "https://mikmaqonline.org/entries/o/oqonitpaqamugwiaq/oqonitpaqamugwiaq.html", "headword": "oqonitpaqamugwiaq", "example_index": 0, "raw_html_path": "raw/entries/481ec1721d82295807c25c1ecf0e25775df251f373294387af2a7810a772d8e7.html", "raw_html_sha256": "b950031f3051c52eb270e484f75acbdba63463ab8c4f6e0bca39ea99c13e8fe6", "fetched_at": "2026-07-12T02:43:01.754Z", "recordings": [ { "recording_id": "e0e5c47b84b23a76446c163e72fc1416b8da02dd574e92cc4f7bf512ba6b0345", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c8c/c8cd8a3ca51fcf225d0e2911ca5060fae37ef549e6e024e12825a49b68a7211a.mp3", "archive_relative_path": "raw/audio/c8c/c8cd8a3ca51fcf225d0e2911ca5060fae37ef549e6e024e12825a49b68a7211a.mp3" } ] } ], "prediction": "Pas'g pas'g a's'g aq gi's gesatg.", "reference": "Pas'g na'n ajiet aq gi's oqonitpaqamugwiaq." }, { "id": "mic-sent-deaea25ecf43c1975ef994b1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who's mask is this?", "output_text": "Wenewei ula jipugje's?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who's mask is this?", "mic_Latn": "Wenewei ula jipugje's?" }, "canonical_ref": "entries/j/jipugje's/jipugje's.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-466ec379a66584af585c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jipugje's/jipugje's.html", "entry_url": "https://mikmaqonline.org/entries/j/jipugje's/jipugje's.html", "headword": "jipugje's", "example_index": 0, "raw_html_path": "raw/entries/fff9111b49dfc920806b6964d1f84013143702d9c59630a74f4f416f070ced1b.html", "raw_html_sha256": "38c6b29bc5e82b48dd4caa0d68f99b70bcc28df911cf81b5bc3085ed754cdf73", "fetched_at": "2026-07-12T02:36:03.229Z", "recordings": [ { "recording_id": "879bfe370b22c10d4c2b5f1fdbd31dc1de6d7ae307b90678ab2253f94e319be8", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2b0/2b073bd178b1d6d6b89fb174d9243d8ff1ca62d3e104479fc09f4c8522f47610.mp3", "archive_relative_path": "raw/audio/2b0/2b073bd178b1d6d6b89fb174d9243d8ff1ca62d3e104479fc09f4c8522f47610.mp3" } ] } ], "prediction": "Wen ugjit na ula?", "reference": "Wenewei ula jipugje's?" }, { "id": "mic-sent-dece17067a94808b573d9e0e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary is very clever, how she lives.", "output_text": "Mali na mawinatawe'g ta'n telmimajit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary is very clever, how she lives.", "mic_Latn": "Mali na mawinatawe'g ta'n telmimajit." }, "canonical_ref": "entries/n/natawe'g/natawe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-804abded40132d4927d8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/natawe'g/natawe'g.html", "entry_url": "https://mikmaqonline.org/entries/n/natawe'g/natawe'g.html", "headword": "natawe'g", "example_index": 0, "raw_html_path": "raw/entries/63891fe9196f4afdf574d92e191004a1fa92037d4cc228811c581803b73986fe.html", "raw_html_sha256": "ae2d423f74b325a182b8024902adbabaf6595e42dd98bc539aeae7d1803e5ef5", "fetched_at": "2026-07-12T02:42:11.679Z", "recordings": [ { "recording_id": "08dca8e81364d8427909b8f97943eda59c2dabead6e1f6d533b0ae05fb7b9501", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6fa/6fa46b30d2640dfd6eb9a0b8a58bee2849207d0fb9d81f0f4827d6ffb175dd75.mp3", "archive_relative_path": "raw/audio/6fa/6fa46b30d2640dfd6eb9a0b8a58bee2849207d0fb9d81f0f4827d6ffb175dd75.mp3" } ] } ], "prediction": "Mali na mawji'jg, ta'n tujiw.", "reference": "Mali na mawinatawe'g ta'n telmimajit." }, { "id": "mic-sent-df772750254ee7ff2beba639:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I would love to be able to find the old newspaper called the \"Migmaoi Solnaltjitj\".", "output_text": "Etna gsatmug gisiwe'jituas sa'qawei sulnalji'j teluisig \"Migmaoi Solnaltjitj\".", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I would love to be able to find the old newspaper called the \"Migmaoi Solnaltjitj\".", "mic_Latn": "Etna gsatmug gisiwe'jituas sa'qawei sulnalji'j teluisig \"Migmaoi Solnaltjitj\"." }, "canonical_ref": "entries/s/sulnalji'j/sulnalji'j.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f71b120347f3d02bf237", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sulnalji'j/sulnalji'j.html", "entry_url": "https://mikmaqonline.org/entries/s/sulnalji'j/sulnalji'j.html", "headword": "sulnalji'j", "example_index": 0, "raw_html_path": "raw/entries/c16b1a445c98c9c29c8397a3f1bf754ef9f2c70dc78d1cca4e133fcf8b734f87.html", "raw_html_sha256": "bed88d06cefff160a00d0eba47125419bbf330f55a39b3399e921e73dfcfab35", "fetched_at": "2026-07-12T02:45:17.032Z", "recordings": [ { "recording_id": "62d0e2edcfba6d3f6ccf27b35c3e508433c6296f36398885ec2856c353875fda", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0a1/0a1d88cf60b63f5b911f948003ff644123ec9152e8bf7d52385b0b49b41eb59b.mp3", "archive_relative_path": "raw/audio/0a1/0a1d88cf60b63f5b911f948003ff644123ec9152e8bf7d52385b0b49b41eb59b.mp3" } ] } ], "prediction": "Pugwelg'p na we'gwi'g wi'gatign \"Migmaoi Solnaltjitj\".", "reference": "Etna gsatmug gisiwe'jituas sa'qawei sulnalji'j teluisig \"Migmaoi Solnaltjitj\"." }, { "id": "mic-sent-e0b666942ebfa41e0d1d4ee1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she pushes his/her buddy when he/she (the buddy) got stuck.", "output_text": "Witapal apt'tesinniteg gesmoqja'lapnn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she pushes his/her buddy when he/she (the buddy) got stuck.", "mic_Latn": "Witapal apt'tesinniteg gesmoqja'lapnn." }, "canonical_ref": "entries/g/gesmoqja'latl/gesmoqja'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2cb90fc989e83484cfaf", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesmoqja'latl/gesmoqja'latl.html", "entry_url": "https://mikmaqonline.org/entries/g/gesmoqja'latl/gesmoqja'latl.html", "headword": "gesmoqja'latl", "example_index": 0, "raw_html_path": "raw/entries/d966ebc1b2dcffda5031af311347e2d643a380d740d5e72c1dbabd63d7c9e9f0.html", "raw_html_sha256": "888bc90e25a85b9d7939e88cc2b317e8cbbdd55eb1347036596052df0e76ccf5", "fetched_at": "2026-07-12T02:39:16.156Z", "recordings": [ { "recording_id": "8470fa5fdf376f048a561cb307766ad1c2fdd2ca2cd941dcbbddb18079a2a07b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6e9/6e9f681ac2b5faf937ac91e02a4e64dbe895162cedcf8eb79c15372cb12ca89b.mp3", "archive_relative_path": "raw/audio/6e9/6e9f681ac2b5faf937ac91e02a4e64dbe895162cedcf8eb79c15372cb12ca89b.mp3" } ] } ], "prediction": "Gesatg ugjitl ta'n tujiw gesatg.", "reference": "Witapal apt'tesinniteg gesmoqja'lapnn." }, { "id": "mic-sent-e0bacd7d96f4c74eb6a40c00:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she looks proud strutting in a new outfit.", "output_text": "Gi'nujing alnasg'g pilei aligew.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she looks proud strutting in a new outfit.", "mic_Latn": "Gi'nujing alnasg'g pilei aligew." }, "canonical_ref": "entries/g/gi'nujing/gi'nujing.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-39cc7ba8dfbb10fe08b3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gi'nujing/gi'nujing.html", "entry_url": "https://mikmaqonline.org/entries/g/gi'nujing/gi'nujing.html", "headword": "gi'nujing", "example_index": 1, "raw_html_path": "raw/entries/1cda6b59c27709a25c86589b36e0b495da3d0a6bb6693c674b3a77e7828b5800.html", "raw_html_sha256": "c91bae5eced9fcc6ba51f3d967e0a3a02d5bd8615e4cd69334d1c8e523597544", "fetched_at": "2026-07-12T02:39:35.251Z", "recordings": [ { "recording_id": "8006879c686488a4d490d61877100c680bb2fadd510f824b055017e069535c5d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a5e/a5ef2855ea3d174e8ba798b0636a1c7c5e4e48a112679c9eb965f9ba868a0178.mp3", "archive_relative_path": "raw/audio/a5e/a5ef2855ea3d174e8ba798b0636a1c7c5e4e48a112679c9eb965f9ba868a0178.mp3" } ] } ], "prediction": "Pugwelga'latl newtepaqanigtug.", "reference": "Gi'nujing alnasg'g pilei aligew." }, { "id": "mic-sent-e15e2944c482454cec83b171:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What is attached to your shirt?", "output_text": "Goqwei megwasteg gtatla'img?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What is attached to your shirt?", "mic_Latn": "Goqwei megwasteg gtatla'img?" }, "canonical_ref": "entries/m/megwasteg/megwasteg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-93f7adefb20bb68d1dea", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/megwasteg/megwasteg.html", "entry_url": "https://mikmaqonline.org/entries/m/megwasteg/megwasteg.html", "headword": "megwasteg", "example_index": 0, "raw_html_path": "raw/entries/f83a675686ef23254b3e28df4a138e8b3970a47cda4d85716a56e34d3f50541c.html", "raw_html_sha256": "b3281de251b720299eb61048edef5a9b66653c214bd524f65c9f409b87fe3971", "fetched_at": "2026-07-12T02:41:09.363Z", "recordings": [ { "recording_id": "6287de602ba817d07564504ce064099039bd2d286fbae5410729716371bc82a1", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f8e/f8ed75b478938575d46ab375ef2659b483e1e64cb41fa43ea80da24bace67f05.mp3", "archive_relative_path": "raw/audio/f8e/f8ed75b478938575d46ab375ef2659b483e1e64cb41fa43ea80da24bace67f05.mp3" } ] } ], "prediction": "Goqwei gisi'g ta'n tujiw ugjit?", "reference": "Goqwei megwasteg gtatla'img?" }, { "id": "mic-sent-e19f8f20bf2caf8e0047260e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Did he/she turn the bedsheet over yet?", "output_text": "Gi's gawasgega'latl na naqsunn?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Did he/she turn the bedsheet over yet?", "mic_Latn": "Gi's gawasgega'latl na naqsunn?" }, "canonical_ref": "entries/g/gawasgega'latl/gawasgega'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-596f12ae9f68995754af", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gawasgega'latl/gawasgega'latl.html", "entry_url": "https://mikmaqonline.org/entries/g/gawasgega'latl/gawasgega'latl.html", "headword": "gawasgega'latl", "example_index": 0, "raw_html_path": "raw/entries/dc3447e7dbf69ab2b2e7883c104dcbd290a5f5ba2182d2262611edcdc3eb0321.html", "raw_html_sha256": "c9ee4b12fdd95695a8a8fef59b7dd2b93c78afadee8ff14db7b5bf63996af91e", "fetched_at": "2026-07-12T02:38:46.227Z", "recordings": [ { "recording_id": "360636cd68e1e5462e916f1ebb3ac3ffa74fb6584915b220e16b769c83090a4b", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/586/586bd4ac01497fd41e45509adf5adc40eff183a08e1f9f72c4581a85f5cbabb6.mp3", "archive_relative_path": "raw/audio/586/586bd4ac01497fd41e45509adf5adc40eff183a08e1f9f72c4581a85f5cbabb6.mp3" } ] } ], "prediction": "Gi's gi's gaqapi'latl?", "reference": "Gi's gawasgega'latl na naqsunn?" }, { "id": "mic-sent-e1df2ab5dfcef59b511e4530:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This food is a bit cold.", "output_text": "Amitgig ula mijipjewei.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This food is a bit cold.", "mic_Latn": "Amitgig ula mijipjewei." }, "canonical_ref": "entries/a/amitgig/amitgig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-42c9675f51229d97e602", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amitgig/amitgig.html", "entry_url": "https://mikmaqonline.org/entries/a/amitgig/amitgig.html", "headword": "amitgig", "example_index": 0, "raw_html_path": "raw/entries/28a4bb4b9b3e48f90f211fd9d7fa761a55048ddcbef806fe0cfb8720228e51b7.html", "raw_html_sha256": "ca92fd2eb2ab3780d0df87d70f1609a72db82bf4540426c21c645ccf03129b4c", "fetched_at": "2026-07-12T02:36:52.220Z", "recordings": [ { "recording_id": "9466c40090da35d32ff840ab5a2796776c4255c027483b8b270a88c6ab8804ba", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/696/6963e516aa7cb52e29902382017884296c304ffb2c1ada4c6b67ce620b2a8248.mp3", "archive_relative_path": "raw/audio/696/6963e516aa7cb52e29902382017884296c304ffb2c1ada4c6b67ce620b2a8248.mp3" } ] } ], "prediction": "Pugwelg na ula gmu'j.", "reference": "Amitgig ula mijipjewei." }, { "id": "mic-sent-e1f074ac484d23dc29d81b27:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she kicks it but probably won't be able to kick it through.", "output_text": "Tegtesg'g gatu etug ma' gis saputetesgmug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she kicks it but probably won't be able to kick it through.", "mic_Latn": "Tegtesg'g gatu etug ma' gis saputetesgmug." }, "canonical_ref": "entries/t/tegtesg'g/tegtesg'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-158f457afae59e65757e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tegtesg'g/tegtesg'g.html", "entry_url": "https://mikmaqonline.org/entries/t/tegtesg'g/tegtesg'g.html", "headword": "tegtesg'g", "example_index": 0, "raw_html_path": "raw/entries/065a7f24bfac2f04fee6e04292b297077bb3c1be8eff83b847750d95658bc2d3.html", "raw_html_sha256": "eed6a9c0dda3eb9c138de5a40d1381ef0aa65a01ab291a3bb75130e377af167e", "fetched_at": "2026-07-12T02:45:28.969Z", "recordings": [ { "recording_id": "4adc9788f0f26e81e08fdd43fe43160e13acecf09dd28f14a3d537e8c56399b6", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/701/701e0c2ff158f48b06dbec6c2f6fb669392ab2436cd6712587968576e8c80fd5.mp3", "archive_relative_path": "raw/audio/701/701e0c2ff158f48b06dbec6c2f6fb669392ab2436cd6712587968576e8c80fd5.mp3" } ] } ], "prediction": "Gesatg, gatu mu getu' mu gesatg.", "reference": "Tegtesg'g gatu etug ma' gis saputetesgmug." }, { "id": "mic-sent-e1fce95ccd3b857351fdd5d8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she airs out his/her shirt before putting it on.", "output_text": "Newjoqwa'latl ugtatlaiml gesgmnaq nasa'lgw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she airs out his/her shirt before putting it on.", "mic_Latn": "Newjoqwa'latl ugtatlaiml gesgmnaq nasa'lgw." }, "canonical_ref": "entries/n/newjoqwa'latl/newjoqwa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-60d522fffd69e9ecb62e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/newjoqwa'latl/newjoqwa'latl.html", "entry_url": "https://mikmaqonline.org/entries/n/newjoqwa'latl/newjoqwa'latl.html", "headword": "newjoqwa'latl", "example_index": 0, "raw_html_path": "raw/entries/4235413f9f46857c1abef79c4a7d1cd688a968fcb9048afec6892b7096cf43e8.html", "raw_html_sha256": "4a159b1aa156717bcb874cbe4c55d554fb271c4e3d5dc1088ba95196adb0b406", "fetched_at": "2026-07-12T02:42:27.068Z", "recordings": [ { "recording_id": "a28a22bfb0ce7c5a608ca9a0093af51d3fe374b288c9d5da29d8e51ff329bded", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f0c/f0c02eb0204e76eea877cce22566d7bf28759bc1557565951882b05dcc6538fc.mp3", "archive_relative_path": "raw/audio/f0c/f0c02eb0204e76eea877cce22566d7bf28759bc1557565951882b05dcc6538fc.mp3" } ] } ], "prediction": "Gesatg ugta'latl ugjit gesgmnaq gesgmatl.", "reference": "Newjoqwa'latl ugtatlaiml gesgmnaq nasa'lgw." }, { "id": "mic-sent-e20e222a01b5725cf8a8dc71:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The little girl is walking along the middle of the road.", "output_text": "E'pite'ji'j pemiet miawe'g awtigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The little girl is walking along the middle of the road.", "mic_Latn": "E'pite'ji'j pemiet miawe'g awtigtug." }, "canonical_ref": "entries/m/miawe'g/miawe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ce9e5a73999fd0c2f5c0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/miawe'g/miawe'g.html", "entry_url": "https://mikmaqonline.org/entries/m/miawe'g/miawe'g.html", "headword": "miawe'g", "example_index": 0, "raw_html_path": "raw/entries/57dbf5faa819778fbca2fd30c625362e766c63b6a09d0c68729b8384c12d0ebe.html", "raw_html_sha256": "5cc5597c59152370834ef7ca49dde06308bbe01156401ce13c2021033d5720ae", "fetched_at": "2026-07-12T02:41:32.340Z", "recordings": [ { "recording_id": "9fc8a644fb9ec7a499f77f4650d7e373452fff67727879d91a1ae10c08c34d6c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a3b/a3b5b4fc17d1d04d4104174d0368b7be69f3de7cff88614fbf78c2e77fe00ee7.mp3", "archive_relative_path": "raw/audio/a3b/a3b5b4fc17d1d04d4104174d0368b7be69f3de7cff88614fbf78c2e77fe00ee7.mp3" } ] } ], "prediction": "E'pite'ji'j etlmisga'latl mijuaqanigtug.", "reference": "E'pite'ji'j pemiet miawe'g awtigtug." }, { "id": "mic-sent-e2d37fbe2b2541e0a53fd2c2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My son overheard me, now he knows what he is to get tomorrow.", "output_text": "Ngwis gisimigustuit, nige' ge'itoq ta'n goqwei msntew sapo'nug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My son overheard me, now he knows what he is to get tomorrow.", "mic_Latn": "Ngwis gisimigustuit, nige' ge'itoq ta'n goqwei msntew sapo'nug." }, "canonical_ref": "entries/m/migustuatl/migustuatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-200e2c50c3eecc26a7ce", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/migustuatl/migustuatl.html", "entry_url": "https://mikmaqonline.org/entries/m/migustuatl/migustuatl.html", "headword": "migustuatl", "example_index": 0, "raw_html_path": "raw/entries/2feed793f599a5c9f0024ddb3f0629293eb1dac79f2eb033911a7136ea4d34f5.html", "raw_html_sha256": "414001589df12d1ee5235d2e9c653cdaa69afa229ba6a90039b8aaab7260420e", "fetched_at": "2026-07-12T02:41:33.845Z", "recordings": [ { "recording_id": "3e764aef49003a3197da527aece0092d5ed61343279d6ceb2f35204443186a79", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fbb/fbb808f7721ff8315d93fd931c621b58b8899acd2b342bbd5425ee24fd96df4c.mp3", "archive_relative_path": "raw/audio/fbb/fbb808f7721ff8315d93fd931c621b58b8899acd2b342bbd5425ee24fd96df4c.mp3" } ] } ], "prediction": "Ngwis gi's na'te'l, nige' ge' gi'l goqwei ta'n te'sipu'nug.", "reference": "Ngwis gisimigustuit, nige' ge'itoq ta'n goqwei msntew sapo'nug." }, { "id": "mic-sent-e3264125d9a36b16052c9689:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That is a noisy old door.", "output_text": "Na we'gwisespe'g na sa'qawei ga'qan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That is a noisy old door.", "mic_Latn": "Na we'gwisespe'g na sa'qawei ga'qan." }, "canonical_ref": "entries/s/sespe'g/sespe'g.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c972baec10ba56af87ae", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sespe'g/sespe'g.html", "entry_url": "https://mikmaqonline.org/entries/s/sespe'g/sespe'g.html", "headword": "sespe'g", "example_index": 1, "raw_html_path": "raw/entries/f6ac441ebf6bee56c7005652f16c350950da756bfb137b5df61d7f63be0b801a.html", "raw_html_sha256": "69c827399d3d4f05126bac8c3a7b23752785a5728a8a50bb302b2b73277d55c6", "fetched_at": "2026-07-12T02:44:52.506Z", "recordings": [ { "recording_id": "136971a2187929f32eb861544097929a4e71b00e8402766dafa57dc0f9d92885", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8aa/8aa50695100ee82b3c3b39989d3168e51dd0bd4cd73be2c694952d8d3ca95ba6.mp3", "archive_relative_path": "raw/audio/8aa/8aa50695100ee82b3c3b39989d3168e51dd0bd4cd73be2c694952d8d3ca95ba6.mp3" } ] } ], "prediction": "We'gwi'g na te'sipu'g.", "reference": "Na we'gwisespe'g na sa'qawei ga'qan." }, { "id": "mic-sent-e394df43e458462b86fefd39:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I don't think there's a day that my dog doesn't shed.", "output_text": "Etug mu eigtnug na'gweg la nti mu pesgwiegw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I don't think there's a day that my dog doesn't shed.", "mic_Latn": "Etug mu eigtnug na'gweg la nti mu pesgwiegw." }, "canonical_ref": "entries/p/pesgwiet/pesgwiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f88a0a31c01335d818c6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pesgwiet/pesgwiet.html", "entry_url": "https://mikmaqonline.org/entries/p/pesgwiet/pesgwiet.html", "headword": "pesgwiet", "example_index": 0, "raw_html_path": "raw/entries/44a843082466a9c8e378763066ffa3d46d8bae4ad0916a5d30a2880f715a2a00.html", "raw_html_sha256": "790b36b38332deca26f1b33a63c299d121329f85d56ef3cf2e4f7563510419ee", "fetched_at": "2026-07-12T02:43:43.062Z", "recordings": [ { "recording_id": "74b18ec706b9a356065c04a1c737de96f41dc210a643283da4d7a4d5a83e6b83", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d31/d31c09809e8de0bff93131895b8a93a7ca687704e54368f3dc27ffd74a4f0d75.mp3", "archive_relative_path": "raw/audio/d31/d31c09809e8de0bff93131895b8a93a7ca687704e54368f3dc27ffd74a4f0d75.mp3" } ] } ], "prediction": "Mu nugu' telte'g na ni'n mimaji'j mima's'g.", "reference": "Etug mu eigtnug na'gweg la nti mu pesgwiegw." }, { "id": "mic-sent-e397a5c0f35040cac702b077:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What is mountain ash used for?", "output_text": "Talwego't na epsmusi?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What is mountain ash used for?", "mic_Latn": "Talwego't na epsmusi?" }, "canonical_ref": "entries/e/epsmusi/epsmusi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5c5c3829b5965b0d38c1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/epsmusi/epsmusi.html", "entry_url": "https://mikmaqonline.org/entries/e/epsmusi/epsmusi.html", "headword": "epsmusi", "example_index": 0, "raw_html_path": "raw/entries/939ce60f6147d8cb65c4a05b2f4a312470bea883ccca122badf9ccedbf2ee816.html", "raw_html_sha256": "b95c6ec6226686a4933c4560160ba484550c79cc601a8d2e09fe57d40e63a295", "fetched_at": "2026-07-12T02:38:11.531Z", "recordings": [ { "recording_id": "0d112cfba09d204e2c9154518732fbedbb388369a5f90250e7bc7b9f22b70c5d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fb7/fb77bcc764cd22fb71ea1fbf52cba1c6756acafa22bf4b4d454e18f36f396700.mp3", "archive_relative_path": "raw/audio/fb7/fb77bcc764cd22fb71ea1fbf52cba1c6756acafa22bf4b4d454e18f36f396700.mp3" } ] } ], "prediction": "Goqwei ta'n tujiw ugjit ugjit?", "reference": "Talwego't na epsmusi?" }, { "id": "mic-sent-e519defe64a260efe61dac73:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I haven't seen anyone harvest hay in a long time.", "output_text": "Sa'q mu wen nemiaq mawsgiget.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I haven't seen anyone harvest hay in a long time.", "mic_Latn": "Sa'q mu wen nemiaq mawsgiget." }, "canonical_ref": "entries/m/mawsgiget/mawsgiget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f08106158cb684ab877d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mawsgiget/mawsgiget.html", "entry_url": "https://mikmaqonline.org/entries/m/mawsgiget/mawsgiget.html", "headword": "mawsgiget", "example_index": 0, "raw_html_path": "raw/entries/a99859dd08273c0df69a8feb54c2244c79ae1d213545a923786e180f6a0dfb77.html", "raw_html_sha256": "82fe4b51f49ca6aeaa0e306b204d8d102a372cf5a2a1da76c93395eeea87571a", "fetched_at": "2026-07-12T02:41:04.624Z", "recordings": [ { "recording_id": "373e3da870e92145cd18ff5c7ce61e7732cdfc56fac436f11b8787bbbc6617e8", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/899/899a17060c586624b955cff628b2128f7f649054c1fa89f542ec61604c3cfe9c.mp3", "archive_relative_path": "raw/audio/899/899a17060c586624b955cff628b2128f7f649054c1fa89f542ec61604c3cfe9c.mp3" } ] } ], "prediction": "Gi's ni'n nemi's'g ta'n tujiw gesgm'g.", "reference": "Sa'q mu wen nemiaq mawsgiget." }, { "id": "mic-sent-e52f68d33d065a9921161482:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Salmon tastes really good.", "output_text": "Plamu na mawwigapugsit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Salmon tastes really good.", "mic_Latn": "Plamu na mawwigapugsit." }, "canonical_ref": "entries/w/wigapugsit/wigapugsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d84694ec7095d0d56ef1", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wigapugsit/wigapugsit.html", "entry_url": "https://mikmaqonline.org/entries/w/wigapugsit/wigapugsit.html", "headword": "wigapugsit", "example_index": 0, "raw_html_path": "raw/entries/874bc35f9ac6d631baa5329b95a0a7446f7b7a7989942c8ab8d2f504e5bd3ac5.html", "raw_html_sha256": "f31ab1f88fbaab12f5e26158d1abff65f999b37af82abd71a7ddbebbd7d45dd6", "fetched_at": "2026-07-12T02:47:28.700Z", "recordings": [ { "recording_id": "8abf453fb7e9110688fb2a8f0e152a9e3c6e786fc76b17ff89e339795efd38fa", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ca7/ca78f3fd8b8aff14da98c4328a41eb27ef7cfd1010ec68cb53b2db3e6aa2b837.mp3", "archive_relative_path": "raw/audio/ca7/ca78f3fd8b8aff14da98c4328a41eb27ef7cfd1010ec68cb53b2db3e6aa2b837.mp3" } ] } ], "prediction": "Plamu'g na we'gwi'g.", "reference": "Plamu na mawwigapugsit." }, { "id": "mic-sent-e578faf48cfb30aa9bc841ef:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she fusses over his/her grandchild and the child totally loves it.", "output_text": "Mega'sualatl uji'tl aq teto'qigsalsnnitl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she fusses over his/her grandchild and the child totally loves it.", "mic_Latn": "Mega'sualatl uji'tl aq teto'qigsalsnnitl." }, "canonical_ref": "entries/m/mega'sualatl/mega'sualatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6634fb0738e01057cae2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mega'sualatl/mega'sualatl.html", "entry_url": "https://mikmaqonline.org/entries/m/mega'sualatl/mega'sualatl.html", "headword": "mega'sualatl", "example_index": 0, "raw_html_path": "raw/entries/e6e79d7e11c213b3c102ef94c76070b76bbb605cbfd96c7fba7559a45b6744c7.html", "raw_html_sha256": "5f77f8df99316d032ee6e63dc1a8c5bc6ca146c1c2c890bc9106866c5fe16529", "fetched_at": "2026-07-12T02:41:05.744Z", "recordings": [ { "recording_id": "f1b4136d777ba124b3a2c1d6c507b7ece92bc5d6431ef2cf8966e5ae786f41bb", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b35/b359d6118668a4194a270b3865bc66ecafee1bacd08af7480089548d8f3838f3.mp3", "archive_relative_path": "raw/audio/b35/b359d6118668a4194a270b3865bc66ecafee1bacd08af7480089548d8f3838f3.mp3" } ] } ], "prediction": "Nujipa'latl ugjitl aq lpa'tuji'j gisijg.", "reference": "Mega'sualatl uji'tl aq teto'qigsalsnnitl." }, { "id": "mic-sent-e5d8d7d997514fbf8f32c971:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The ladder is leaning up against the house.", "output_text": "Lgusuaqan epatgupuguig wenji'guomg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The ladder is leaning up against the house.", "mic_Latn": "Lgusuaqan epatgupuguig wenji'guomg." }, "canonical_ref": "entries/e/epatgupuguig/epatgupuguig.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-715c454e083ca501c24f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/epatgupuguig/epatgupuguig.html", "entry_url": "https://mikmaqonline.org/entries/e/epatgupuguig/epatgupuguig.html", "headword": "epatgupuguig", "example_index": 0, "raw_html_path": "raw/entries/2ccb36c408a8e2b38b1fc6ef87f1ff21f8d660300625ec2d8d18a7fd33250c82.html", "raw_html_sha256": "51b548aef75a7db743452f940350f16068c1a75a5b4398caab57f875d96f5653", "fetched_at": "2026-07-12T02:38:06.807Z", "recordings": [ { "recording_id": "4b775be33141e3dcea813fe5279112471100acef83f615711da00d656f5cdd75", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/413/413c4c7cf644724a3f6a4520c76b84c94c83dca484f34eafdfff13dbeaed9f65.mp3", "archive_relative_path": "raw/audio/413/413c4c7cf644724a3f6a4520c76b84c94c83dca484f34eafdfff13dbeaed9f65.mp3" } ] } ], "prediction": "Lpa wi'gwi'g na gmu'ji'j.", "reference": "Lgusuaqan epatgupuguig wenji'guomg." }, { "id": "mic-sent-e5ebb22768b9ac4ab897e739:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Johnny already left, he's gone fishing.", "output_text": "Jonio'q gi's maja'sitaq, najiwsgetaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Johnny already left, he's gone fishing.", "mic_Latn": "Jonio'q gi's maja'sitaq, najiwsgetaq." }, "canonical_ref": "entries/n/najiwsget/najiwsget.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-7b0ce3dd865c79ce1ff6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/najiwsget/najiwsget.html", "entry_url": "https://mikmaqonline.org/entries/n/najiwsget/najiwsget.html", "headword": "najiwsget", "example_index": 0, "raw_html_path": "raw/entries/feb7c1a8c459372a168f1f813bf447f5b3e5f35e1e27a4e29dec88549454ea4d.html", "raw_html_sha256": "a40c1166a1feb51c0fd6a19f18a92718b1757ce665c47962f969f5c3fa3caa04", "fetched_at": "2026-07-12T02:41:57.082Z", "recordings": [ { "recording_id": "aaf3b8cabf06773004cec95e8d36e67f139654422a18eaffaf933965e606e754", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0d2/0d252a48d3c5f5ea03662a55c5eef7ad6eab4af61323cf4987f7a702260805ff.mp3", "archive_relative_path": "raw/audio/0d2/0d252a48d3c5f5ea03662a55c5eef7ad6eab4af61323cf4987f7a702260805ff.mp3" } ] } ], "prediction": "Gi'nnie'j gi's gi'l, pugsugwet.", "reference": "Jonio'q gi's maja'sitaq, najiwsgetaq." }, { "id": "mic-sent-e5f3f2b75dd00b1da60003ff:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is in the barn, working in secret.", "output_text": "Wesgowa'sit legla'nsigtug, etlgimilugwet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is in the barn, working in secret.", "mic_Latn": "Wesgowa'sit legla'nsigtug, etlgimilugwet." }, "canonical_ref": "entries/g/gimilugwet/gimilugwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3bdb73aa6ce59433afee", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gimilugwet/gimilugwet.html", "entry_url": "https://mikmaqonline.org/entries/g/gimilugwet/gimilugwet.html", "headword": "gimilugwet", "example_index": 0, "raw_html_path": "raw/entries/b8f83db766510697cd81bdceb7ae85ab19b60a48759bf690569c9cd86692c7d3.html", "raw_html_sha256": "5205f5e61960d2c953db5e06569b59cbd646d361641ecba49a86084d7eea11f8", "fetched_at": "2026-07-12T02:39:33.140Z", "recordings": [ { "recording_id": "1f0fe68a5c778ccf1b4f842224351d2f6197e4f337075ef72d0cc7608439ba31", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/117/11713eb3a90661bbdebd326d5a9998afbf7b7f5d9d5617f1abcc190324a64e11.mp3", "archive_relative_path": "raw/audio/117/11713eb3a90661bbdebd326d5a9998afbf7b7f5d9d5617f1abcc190324a64e11.mp3" } ] } ], "prediction": "Lpa etlpugwet, lugowa'sit.", "reference": "Wesgowa'sit legla'nsigtug, etlgimilugwet." }, { "id": "mic-sent-e6bfbc693914df0d6ff1aed7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "We barely were able to pry our boat loose when it got stuck on the rocks.", "output_text": "Waqqaj pegwigwatmeg ntulninen ta'njiw apjimoqtesgeg guntewigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "We barely were able to pry our boat loose when it got stuck on the rocks.", "mic_Latn": "Waqqaj pegwigwatmeg ntulninen ta'njiw apjimoqtesgeg guntewigtug." }, "canonical_ref": "entries/p/pegwigwatg/pegwigwatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ad4ad73ed45ace940207", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pegwigwatg/pegwigwatg.html", "entry_url": "https://mikmaqonline.org/entries/p/pegwigwatg/pegwigwatg.html", "headword": "pegwigwatg", "example_index": 0, "raw_html_path": "raw/entries/b8a714c4ebebe08ee77f601d274639cedb59e291c80afb8da15d54aaea0b47fd.html", "raw_html_sha256": "ff6e6a6397a56c8062a74087ba68e9b6863c5a0040af4de7566887f6717c3274", "fetched_at": "2026-07-12T02:43:23.757Z", "recordings": [ { "recording_id": "123ecabe3bcb24d5e70050e7d1741c2933e55a4209fb2bdc584ddae969ee37e1", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1b2/1b2fc98cab2b3425e4cea88f31ab9c7ef7cc3426af8c23fb36a9502b6e59c7b4.mp3", "archive_relative_path": "raw/audio/1b2/1b2fc98cab2b3425e4cea88f31ab9c7ef7cc3426af8c23fb36a9502b6e59c7b4.mp3" } ] } ], "prediction": "Gi's ni'n tujiw nugu' gesatg ta'n te'sijig.", "reference": "Waqqaj pegwigwatmeg ntulninen ta'njiw apjimoqtesgeg guntewigtug." }, { "id": "mic-sent-e6e3a2653974431f8e1f1e44:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's high up where you and I are working.", "output_text": "Esp'teg na ula etlugweigw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's high up where you and I are working.", "mic_Latn": "Esp'teg na ula etlugweigw." }, "canonical_ref": "entries/e/esp'teg/esp'teg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f300faf50abbf7911b3b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/esp'teg/esp'teg.html", "entry_url": "https://mikmaqonline.org/entries/e/esp'teg/esp'teg.html", "headword": "esp'teg", "example_index": 0, "raw_html_path": "raw/entries/6fcb4c31d7a403a53c4658e71f3fb1d021e86e4befb4bb4ebc18c7a9a79f2542.html", "raw_html_sha256": "da20964adb5e496e8cd25a888f910a1b115cf7d7221b11c8a5c26c943fd24948", "fetched_at": "2026-07-12T02:38:20.177Z", "recordings": [ { "recording_id": "a45e69427dc12c58f76abd5d5a4631d8c6817aac421f0027c9c716e14bdfa7ac", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a60/a60aa10bc4f8a1e29a8b66e2b5ad595d7bbfa12f3d5ca1481858479198c57d7b.mp3", "archive_relative_path": "raw/audio/a60/a60aa10bc4f8a1e29a8b66e2b5ad595d7bbfa12f3d5ca1481858479198c57d7b.mp3" } ] } ], "prediction": "Pugwelg ta'n tujiw nige' etlugowaqan.", "reference": "Esp'teg na ula etlugweigw." }, { "id": "mic-sent-e747e9ebe13a1270dab2bcc9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Let's use the fan, that way it will be cooler.", "output_text": "Iga'tunej ugju'snei, me' na ulnewetew.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Let's use the fan, that way it will be cooler.", "mic_Latn": "Iga'tunej ugju'snei, me' na ulnewetew." }, "canonical_ref": "entries/u/ugju'snei/ugju'snei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8c792fc3aa100e3562c8", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugju'snei/ugju'snei.html", "entry_url": "https://mikmaqonline.org/entries/u/ugju'snei/ugju'snei.html", "headword": "ugju'snei", "example_index": 0, "raw_html_path": "raw/entries/6e06a40cb52ef02826ec5929182adef77179ef65995052cc79322d9a7352a729.html", "raw_html_sha256": "ff850fe0091675224e007b82f4de6e9296c9a0c82901e309dd642976b9498eb1", "fetched_at": "2026-07-12T02:46:12.519Z", "recordings": [ { "recording_id": "aa2ab13c7ebb6f5cf1d21814d725b88d89568f54ab62e6cef29b02a76fe1434b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/312/312acf05ebfd421673f6b316c353d7203235ff4c5cfaceb6a8ee2603e78d76c1.mp3", "archive_relative_path": "raw/audio/312/312acf05ebfd421673f6b316c353d7203235ff4c5cfaceb6a8ee2603e78d76c1.mp3" } ] } ], "prediction": "Amujpa'tu'n, na me' we'gwi'g'p.", "reference": "Iga'tunej ugju'snei, me' na ulnewetew." }, { "id": "mic-sent-e79f39a664ec27aa96aa597e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A virus does spread quickly.", "output_text": "Gsnugowaqan mawjaqalse'sa's'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A virus does spread quickly.", "mic_Latn": "Gsnugowaqan mawjaqalse'sa's'g." }, "canonical_ref": "entries/s/se'sa's'g/se'sa's'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dbd46d7e4103cd57d516", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/se'sa's'g/se'sa's'g.html", "entry_url": "https://mikmaqonline.org/entries/s/se'sa's'g/se'sa's'g.html", "headword": "se'sa's'g", "example_index": 0, "raw_html_path": "raw/entries/b8c60e4510cccd0ec7cbb274d26a69abb6faff50c57650292516e2533f302d1c.html", "raw_html_sha256": "6b72ea3702ebf6fe137b57c2e2fd1b77e0b7cfd14351ab9ab97896e85f99a473", "fetched_at": "2026-07-12T02:44:51.487Z", "recordings": [ { "recording_id": "bdce983825aafb1224281181cd1e4f1ce5d90c44a4db44909bba80242c212cbd", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/83b/83b60d120a5ff7fc6c7d0a0656e4478686ba8d24b4e6c384284c8d58d23ba8b7.mp3", "archive_relative_path": "raw/audio/83b/83b60d120a5ff7fc6c7d0a0656e4478686ba8d24b4e6c384284c8d58d23ba8b7.mp3" } ] } ], "prediction": "We'gwi'g na mawji'j.", "reference": "Gsnugowaqan mawjaqalse'sa's'g." }, { "id": "mic-sent-e85462b4e3ea6da7641fb82c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she puts in maximum effort when he/she is helping people.", "output_text": "Lpa na gaqiga'lsit ta'n tujiw mimajuiu'g apoqonmuaj.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she puts in maximum effort when he/she is helping people.", "mic_Latn": "Lpa na gaqiga'lsit ta'n tujiw mimajuiu'g apoqonmuaj." }, "canonical_ref": "entries/g/gaqiga'lsit/gaqiga'lsit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-94c1e4bfb4b0c9d81669", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gaqiga'lsit/gaqiga'lsit.html", "entry_url": "https://mikmaqonline.org/entries/g/gaqiga'lsit/gaqiga'lsit.html", "headword": "gaqiga'lsit", "example_index": 0, "raw_html_path": "raw/entries/0c3adb5eff9cbb6a21b357b81284548c80263c1475f50400d552980e04d70996.html", "raw_html_sha256": "9370f8d62b499bb389ad53e99ec0f9060461ec3192937285a1dc60a3836bf9c7", "fetched_at": "2026-07-12T02:38:40.884Z", "recordings": [ { "recording_id": "cb12a1722889b83de92791d18abfa2a6a9660e9024b56c4acc91b5969a92d20c", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/68d/68d91f41c75bf94c841b2ec41d31c87f9c5e81257de29db7a167ea834ca0b43b.mp3", "archive_relative_path": "raw/audio/68d/68d91f41c75bf94c841b2ec41d31c87f9c5e81257de29db7a167ea834ca0b43b.mp3" } ] } ], "prediction": "Pugwelga'sit ta'n tujiw gisgug.", "reference": "Lpa na gaqiga'lsit ta'n tujiw mimajuiu'g apoqonmuaj." }, { "id": "mic-sent-e86edc963488e120b4fe4a21:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Here, take this apple.", "output_text": "Ula wenju'su'n ugsua'tu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Here, take this apple.", "mic_Latn": "Ula wenju'su'n ugsua'tu." }, "canonical_ref": "entries/u/ula/ula.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5388a30d5757a74c7f8c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ula/ula.html", "entry_url": "https://mikmaqonline.org/entries/u/ula/ula.html", "headword": "ula", "example_index": 0, "raw_html_path": "raw/entries/428af50b6068fea0c94a4e94a1756b377caee2eaec34ca7502c64213fd313cd2.html", "raw_html_sha256": "d7ad4af5f522a386778fdd6f2de7e3eaea0fa3e386776d375ceff8d5b0dea6c6", "fetched_at": "2026-07-12T02:46:21.857Z", "recordings": [ { "recording_id": "c8ab2d719b2fa2327f3c4a5f854c85a108953b04029380e6a7b009c74495463e", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/89d/89dc93aec29f4c8bfa7c28e256b6af25ac96e8744d9e864621864f8628bf71d1.mp3", "archive_relative_path": "raw/audio/89d/89dc93aec29f4c8bfa7c28e256b6af25ac96e8744d9e864621864f8628bf71d1.mp3" } ] } ], "prediction": "Ula, ula ap'l.", "reference": "Ula wenju'su'n ugsua'tu." }, { "id": "mic-sent-e87119b11b13a8a44558b764:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What do you think he/she is looking for?", "output_text": "Etug goqwei algwilg?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What do you think he/she is looking for?", "mic_Latn": "Etug goqwei algwilg?" }, "canonical_ref": "entries/g/goqwei/goqwei.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6b29a92ffdff43b9044c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/goqwei/goqwei.html", "entry_url": "https://mikmaqonline.org/entries/g/goqwei/goqwei.html", "headword": "goqwei", "example_index": 0, "raw_html_path": "raw/entries/a7332a6f84693605546aae9b59aed9bb4453c2d78127aa3e911a35457cd745eb.html", "raw_html_sha256": "64abf0cfb058148c0786f1e4f724123080335f6d5a05cc9eeadae5e99248d18a", "fetched_at": "2026-07-12T02:39:55.660Z", "recordings": [ { "recording_id": "96f8a495d752a29cad4a735d9db80e27abe89f62417316de267389a6c5aa5a25", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a8a/a8af52bb0ffbae65c8556a93d524398cd28a257a937415d1924ac6959364bfd0.mp3", "archive_relative_path": "raw/audio/a8a/a8af52bb0ffbae65c8556a93d524398cd28a257a937415d1924ac6959364bfd0.mp3" } ] } ], "prediction": "Goqwei ta'n telta'sit?", "reference": "Etug goqwei algwilg?" }, { "id": "mic-sent-e87a534f27c77321e1526b7d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she just glances at his/her book.", "output_text": "Pas'g gipoqapt'g ugtwi'gatign.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she just glances at his/her book.", "mic_Latn": "Pas'g gipoqapt'g ugtwi'gatign." }, "canonical_ref": "entries/g/gipoqapt'g/gipoqapt'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a061b8b66910a4fdda60", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gipoqapt'g/gipoqapt'g.html", "entry_url": "https://mikmaqonline.org/entries/g/gipoqapt'g/gipoqapt'g.html", "headword": "gipoqapt'g", "example_index": 0, "raw_html_path": "raw/entries/c2deb827ab55ef42b128ad983ac60fd1771e289716f81db256c7d42d1be0cb20.html", "raw_html_sha256": "738604b5469e69ef1cf3887483708cb81852f3807afd5246b7fc7a70f83e540b", "fetched_at": "2026-07-12T02:39:35.443Z", "recordings": [ { "recording_id": "aef7b40cbf040ff8f2bb9a6adc1bbfeac0efa31518edfef9e2b587618c1dda16", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/3df/3dfba2946ec4a537b408e130718834c407c5a73e0f2db138b327e46e61769172.mp3", "archive_relative_path": "raw/audio/3df/3dfba2946ec4a537b408e130718834c407c5a73e0f2db138b327e46e61769172.mp3" } ] } ], "prediction": "Pas'g gesatg ugta'latl ugjitl.", "reference": "Pas'g gipoqapt'g ugtwi'gatign." }, { "id": "mic-sent-e930f08288148a1ebf3ebe39:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A female westerner is here to sing to us.", "output_text": "Tg'snugowi'sgw pejigtapegiewugsieg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A female westerner is here to sing to us.", "mic_Latn": "Tg'snugowi'sgw pejigtapegiewugsieg." }, "canonical_ref": "entries/t/tg'snugowi'sgw/tg'snugowi'sgw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-81fa34a072298b8b8251", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tg'snugowi'sgw/tg'snugowi'sgw.html", "entry_url": "https://mikmaqonline.org/entries/t/tg'snugowi'sgw/tg'snugowi'sgw.html", "headword": "tg'snugowi'sgw", "example_index": 0, "raw_html_path": "raw/entries/7986708e40ad608977578945617223bcfbbd9dd0c6725a05f4c6f876f9457d07.html", "raw_html_sha256": "cd390d509d43daa1b37132d80f53c26b68a3869328c529106ad1d53a4114de4f", "fetched_at": "2026-07-12T02:45:56.619Z", "recordings": [ { "recording_id": "e44c40434b07f382dba7818fa1b1ab1e5514560931a093a0cfb9553276e1887f", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/273/273e603af4bd14d8f41b5117bd23cf008acbdfd18037cdf29d33df0d1ef996aa.mp3", "archive_relative_path": "raw/audio/273/273e603af4bd14d8f41b5117bd23cf008acbdfd18037cdf29d33df0d1ef996aa.mp3" } ] } ], "prediction": "E'pite'ji'j na ula gmu'j a'te'l.", "reference": "Tg'snugowi'sgw pejigtapegiewugsieg." }, { "id": "mic-sent-e97fff1cb48541b56ad60ee6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Once he/she started to go wrong everything went wrong around him/her.", "output_text": "Newt amsalieteg negm na ms't goqwei piluei amsala's'g ugtinneg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Once he/she started to go wrong everything went wrong around him/her.", "mic_Latn": "Newt amsalieteg negm na ms't goqwei piluei amsala's'g ugtinneg." }, "canonical_ref": "entries/a/amsaliet/amsaliet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-95fb9da8ac6086d07c20", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amsaliet/amsaliet.html", "entry_url": "https://mikmaqonline.org/entries/a/amsaliet/amsaliet.html", "headword": "amsaliet", "example_index": 0, "raw_html_path": "raw/entries/c7cb7e2b6fd646e88c62d19f8b11ce64f58e4cc43123830c9c0ac1c2d2d1ac2a.html", "raw_html_sha256": "f28273ec9550b4d653a559cc9cea02af7e5b5320cde719a0f0de67dcd160eb10", "fetched_at": "2026-07-12T02:36:55.645Z", "recordings": [ { "recording_id": "38f344db7f2e096e59b13578db182017dd35562e8d1c23d33ee2ae9421293f55", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/1de/1de739e5b2bbbe980c99475ddc6f49538ef1f79ac94cfbceb012935b6a922665.mp3", "archive_relative_path": "raw/audio/1de/1de739e5b2bbbe980c99475ddc6f49538ef1f79ac94cfbceb012935b6a922665.mp3" } ] } ], "prediction": "Newt poqji'j etlmisga'toq ms't goqwei.", "reference": "Newt amsalieteg negm na ms't goqwei piluei amsala's'g ugtinneg." }, { "id": "mic-sent-e9ed02fbbce2d1c85de007f2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Mary is carrying her new doll along.", "output_text": "Mali pemapilatl pile'l ugtapsute'gann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Mary is carrying her new doll along.", "mic_Latn": "Mali pemapilatl pile'l ugtapsute'gann." }, "canonical_ref": "entries/p/pemapilatl/pemapilatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-dbdf99f047792c1e63e2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pemapilatl/pemapilatl.html", "entry_url": "https://mikmaqonline.org/entries/p/pemapilatl/pemapilatl.html", "headword": "pemapilatl", "example_index": 0, "raw_html_path": "raw/entries/c61e892e56cc53d355ca35173de5e3f6c329ad82a5137bf4ac184f49e7f6bb2b.html", "raw_html_sha256": "34c47748fc66f2b1203464776d683b61e13fee1f1126f7e9a246e8e6e7b63c1c", "fetched_at": "2026-07-12T02:43:29.398Z", "recordings": [ { "recording_id": "a27a9810335898d231f1da6b7b412bac0b4690eb24303a931639a49ef4c8a803", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/5d5/5d5436b6f62f63234df7e02b2c037a6e278744d51e732dd35406f08770f293f0.mp3", "archive_relative_path": "raw/audio/5d5/5d5436b6f62f63234df7e02b2c037a6e278744d51e732dd35406f08770f293f0.mp3" } ] } ], "prediction": "Mali na'te'l ugtatla'latl ugjitl.", "reference": "Mali pemapilatl pile'l ugtapsute'gann." }, { "id": "mic-sent-ea55e12b4923dced37007792:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Pussy willows open earliest in the spring.", "output_text": "Nmu'ji'jmnaqsi'g mawnaqsipanita'jig siggw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Pussy willows open earliest in the spring.", "mic_Latn": "Nmu'ji'jmnaqsi'g mawnaqsipanita'jig siggw." }, "canonical_ref": "entries/n/nmu'ji'jmnaqsi/nmu'ji'jmnaqsi.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-585d4e6edc604a933f1e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nmu'ji'jmnaqsi/nmu'ji'jmnaqsi.html", "entry_url": "https://mikmaqonline.org/entries/n/nmu'ji'jmnaqsi/nmu'ji'jmnaqsi.html", "headword": "nmu'ji'jmnaqsi", "example_index": 0, "raw_html_path": "raw/entries/3f385875f98bfd7b13a8fd6f73d819d8c3ce0c6355f3cac88562f199f6afaedb.html", "raw_html_sha256": "a8f81d68f4ac8c2396d5bde8ef59a36e8cf28e33b0d7d3c7089ec3cf8b9d1733", "fetched_at": "2026-07-12T02:42:40.852Z", "recordings": [ { "recording_id": "d401fe98a9c91f2f4c317c9fcfe9ca65af949455e1ef803ac40ccff72932f9e1", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/995/995e09076a1034d4bfe67c7d3fec32ef032bfa8b120febb3a74099847ca9fee5.mp3", "archive_relative_path": "raw/audio/995/995e09076a1034d4bfe67c7d3fec32ef032bfa8b120febb3a74099847ca9fee5.mp3" } ] } ], "prediction": "Gaju'ji'j gaqa'toq te's'g ta'n tujiw ugjit.", "reference": "Nmu'ji'jmnaqsi'g mawnaqsipanita'jig siggw." }, { "id": "mic-sent-ead1eb1d85b74e8111749e06:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It wasn't too long, he/she awoke and regained consciousness.", "output_text": "Mu wasmaipgije'gtnugup wapiet aq nestu'et.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It wasn't too long, he/she awoke and regained consciousness.", "mic_Latn": "Mu wasmaipgije'gtnugup wapiet aq nestu'et." }, "canonical_ref": "entries/n/nestu'et/nestu'et.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6428025caf23920ca4dd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nestu'et/nestu'et.html", "entry_url": "https://mikmaqonline.org/entries/n/nestu'et/nestu'et.html", "headword": "nestu'et", "example_index": 1, "raw_html_path": "raw/entries/92803ce3c98fa664f1a2e4996378d24a828e760595ebc8e15be30261f60ba50f.html", "raw_html_sha256": "f49aa252222ab79bf36d98d271bfa14cecbf6d36d9b6a475197a808838402162", "fetched_at": "2026-07-12T02:42:23.751Z", "recordings": [ { "recording_id": "50528ef23bd0fba498656017ed7d7e3a7f2195703abddf7f3fe6bc2ba717b510", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ff0/ff04aa74284f887e09bf4d37ed0f3e34c6db7af610f255a9b5a2e4739f886e16.mp3", "archive_relative_path": "raw/audio/ff0/ff04aa74284f887e09bf4d37ed0f3e34c6db7af610f255a9b5a2e4739f886e16.mp3" } ] } ], "prediction": "Mu te'sijig, gesatg aq gisga'sit.", "reference": "Mu wasmaipgije'gtnugup wapiet aq nestu'et." }, { "id": "mic-sent-eaf21ca46ecc2532f3fd4059:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My friend here wants to photograph everything.", "output_text": "Ula nitap ms't goqwei getu'napui'g'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My friend here wants to photograph everything.", "mic_Latn": "Ula nitap ms't goqwei getu'napui'g'g." }, "canonical_ref": "entries/n/napui'g'g/napui'g'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-4633ba83a908a08f0556", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/napui'g'g/napui'g'g.html", "entry_url": "https://mikmaqonline.org/entries/n/napui'g'g/napui'g'g.html", "headword": "napui'g'g", "example_index": 0, "raw_html_path": "raw/entries/cabd3b621a4660a6796451662a9e045ca8c510b11c8ef531cdb741caff8ef9fc.html", "raw_html_sha256": "91d1346002a4d5243d33c3bfe07f6c213c0b62cd1cd55c7fa7914dc3ef08b89a", "fetched_at": "2026-07-12T02:42:01.212Z", "recordings": [ { "recording_id": "69ebcbe6acde21a75cebe95b2ceaf262978337274637823a6fe49e99f54f0fa1", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/692/69259fd576c56481b05254af942dc22accce13c2e9e7222b91db4c3c4753ea87.mp3", "archive_relative_path": "raw/audio/692/69259fd576c56481b05254af942dc22accce13c2e9e7222b91db4c3c4753ea87.mp3" } ] } ], "prediction": "Ula nitap ge's goqwei te's'g ta'n tujiw.", "reference": "Ula nitap ms't goqwei getu'napui'g'g." }, { "id": "mic-sent-eb10d8413a22b9e432623392:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "When the ice starts to melt is the most dangerous time for falling into the water.", "output_text": "Poqjinujguma'q mgumi na mawinsanoqon paqasiemg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "When the ice starts to melt is the most dangerous time for falling into the water.", "mic_Latn": "Poqjinujguma'q mgumi na mawinsanoqon paqasiemg." }, "canonical_ref": "entries/p/paqasiet/paqasiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1afb95b5811d55214402", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/paqasiet/paqasiet.html", "entry_url": "https://mikmaqonline.org/entries/p/paqasiet/paqasiet.html", "headword": "paqasiet", "example_index": 0, "raw_html_path": "raw/entries/27048733bd30651a119f3bec4566b78520d353a0278e2069b853f817ae51c107.html", "raw_html_sha256": "f8a6f4d5dac2d6b34f5bb1ea663d97e10be2f5213367ab4115a1af9ebae0ee39", "fetched_at": "2026-07-12T02:43:11.096Z", "recordings": [ { "recording_id": "abb9bf9fb0b38ec54b00e25c66346f776e573e2ac051d0ed446fd82e5a5c3c11", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f4c/f4cbe2126c9482c6e9e0536fa8929a4c7c198bd17d19cd953fda4562fc0a081b.mp3", "archive_relative_path": "raw/audio/f4c/f4cbe2126c9482c6e9e0536fa8929a4c7c198bd17d19cd953fda4562fc0a081b.mp3" } ] } ], "prediction": "Ta'n ta'n tujiw gmu'j poqji'jg na maw we'gwi'gigtug.", "reference": "Poqjinujguma'q mgumi na mawinsanoqon paqasiemg." }, { "id": "mic-sent-eb4bb4a8b7a6090b44dba966:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A plate is called lasiet in the east.", "output_text": "Eptaqan na ugjipenug telui'tut lasiet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A plate is called lasiet in the east.", "mic_Latn": "Eptaqan na ugjipenug telui'tut lasiet." }, "canonical_ref": "entries/l/lasiet/lasiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-bada4738e3855b33f7dd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/l/lasiet/lasiet.html", "entry_url": "https://mikmaqonline.org/entries/l/lasiet/lasiet.html", "headword": "lasiet", "example_index": 0, "raw_html_path": "raw/entries/6b4ffc378821ae349bd51a93f8ae8b19acb8ba279ffde8b62561e0614f42dc7d.html", "raw_html_sha256": "b73eb95f41486ab0c8fbdf6d8704b1dc5da32f20880c5f068f62697a801a44d5", "fetched_at": "2026-07-12T02:40:32.484Z", "recordings": [ { "recording_id": "8b7c7c01be8950ab840de0d7191d2384e7788ee6df9e46542afd127fbf1fb56c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9f2/9f2766662eb656cb017438959bc510451698d718f037fb96b873869e4a3aac15.mp3", "archive_relative_path": "raw/audio/9f2/9f2766662eb656cb017438959bc510451698d718f037fb96b873869e4a3aac15.mp3" } ] } ], "prediction": "Pilei etlma'toq lasiet gisigtug.", "reference": "Eptaqan na ugjipenug telui'tut lasiet." }, { "id": "mic-sent-ebb183b4160652c8d044172f:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The bigger the dog the more foam he/she has in his/her mouth.", "output_text": "Ta'n telgilg nmu'j na telpiampisewtuna't.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The bigger the dog the more foam he/she has in his/her mouth.", "mic_Latn": "Ta'n telgilg nmu'j na telpiampisewtuna't." }, "canonical_ref": "entries/p/pisewtuna't/pisewtuna't.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2c85b65c7106d7eaeea4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pisewtuna't/pisewtuna't.html", "entry_url": "https://mikmaqonline.org/entries/p/pisewtuna't/pisewtuna't.html", "headword": "pisewtuna't", "example_index": 0, "raw_html_path": "raw/entries/c5697a9f078e9116dd73c8697c22f1a405695f8ab9147195b304844d2cfad0f3.html", "raw_html_sha256": "2b2d37390c1dc58bb4090f4a6d29f3dff700c664c222fe98c648aab69144ab76", "fetched_at": "2026-07-12T02:44:01.975Z", "recordings": [ { "recording_id": "8f8c49bf9707157df5c395ff1bf64b3053dcd7d8111673bee00a4c6c57fac791", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/aca/aca714bf762e9017b3ccaff7e1c66357b63c566e0be9b63b37e2e7a2cac21815.mp3", "archive_relative_path": "raw/audio/aca/aca714bf762e9017b3ccaff7e1c66357b63c566e0be9b63b37e2e7a2cac21815.mp3" } ] } ], "prediction": "Ta'n te'sijig ugti ta'n tujiw gesgm'g.", "reference": "Ta'n telgilg nmu'j na telpiampisewtuna't." }, { "id": "mic-sent-ebb6e9fb27971ad97643c536:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she bundles up his/her child, it must be cold.", "output_text": "Elpiso'tulatl unjann, amuj tege'g", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she bundles up his/her child, it must be cold.", "mic_Latn": "Elpiso'tulatl unjann, amuj tege'g" }, "canonical_ref": "entries/e/elpiso'tulatl/elpiso'tulatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-370c728be64d12029edb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elpiso'tulatl/elpiso'tulatl.html", "entry_url": "https://mikmaqonline.org/entries/e/elpiso'tulatl/elpiso'tulatl.html", "headword": "elpiso'tulatl", "example_index": 0, "raw_html_path": "raw/entries/a1a54fb5f56b584622d573ce63d7e8ee27317045f87e7258d4b57e39e1219ab7.html", "raw_html_sha256": "e53580ae3bae4b228143ac1a0c9e5e31f4a345feeec8798335d167d30ea3a7b6", "fetched_at": "2026-07-12T02:37:50.634Z", "recordings": [ { "recording_id": "d0f3b8c2f5f3ac849da4d84dc22ef8e4f575f5bc24bb1707f1fb1df008d3338d", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/039/0390f3dfce0e647f0b85adeeef986dc3c6939690d69eefc0f2d7a53dae58fd49.mp3", "archive_relative_path": "raw/audio/039/0390f3dfce0e647f0b85adeeef986dc3c6939690d69eefc0f2d7a53dae58fd49.mp3" } ] } ], "prediction": "Amujpa'latl unjann, amujpa wesgowaqan.", "reference": "Elpiso'tulatl unjann, amuj tege'g" }, { "id": "mic-sent-ebf750e2b8c29fc90d881315:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "We will sleep in Port Hood, N.S. tonight.", "output_text": "Gwe'gwiamgeg tlne'p'titesnen ulo'nug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "We will sleep in Port Hood, N.S. tonight.", "mic_Latn": "Gwe'gwiamgeg tlne'p'titesnen ulo'nug." }, "canonical_ref": "entries/g/gwe'gwiamgeg/gwe'gwiamgeg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d5e89eda7bd58c87be22", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gwe'gwiamgeg/gwe'gwiamgeg.html", "entry_url": "https://mikmaqonline.org/entries/g/gwe'gwiamgeg/gwe'gwiamgeg.html", "headword": "gwe'gwiamgeg", "example_index": 0, "raw_html_path": "raw/entries/540b56c1f50c8ddbeefdaeb3dc067d26cfc6ec786af6c91341f2a75b13d8b4f0.html", "raw_html_sha256": "7d7345fb2e76c9a37853d6eb37b9da811a9fa48a7222984c34f18c391f283c7f", "fetched_at": "2026-07-12T02:40:02.406Z", "recordings": [ { "recording_id": "02eec7142eb2e06a8d345e6584b579ab7936b93e26c80d3a7b1576406a97d8a8", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d6e/d6ecb36f9d09095652f5d7b9cbb9e02061f08c6afe49a8889d1a975887367c67.mp3", "archive_relative_path": "raw/audio/d6e/d6ecb36f9d09095652f5d7b9cbb9e02061f08c6afe49a8889d1a975887367c67.mp3" } ] } ], "prediction": "We'gwi'jig na Port Hood, N.S. gisgug.", "reference": "Gwe'gwiamgeg tlne'p'titesnen ulo'nug." }, { "id": "mic-sent-ec183b8e8022e5eb8bc43efb:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My daughter is happiest stiring something sweet.", "output_text": "Ntus maw ulte'teget natgoqwei seggw etlmesiapo'q'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My daughter is happiest stiring something sweet.", "mic_Latn": "Ntus maw ulte'teget natgoqwei seggw etlmesiapo'q'g." }, "canonical_ref": "entries/m/mesiapo'q'g/mesiapo'q'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-268337c7cdebd9c432d3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mesiapo'q'g/mesiapo'q'g.html", "entry_url": "https://mikmaqonline.org/entries/m/mesiapo'q'g/mesiapo'q'g.html", "headword": "mesiapo'q'g", "example_index": 0, "raw_html_path": "raw/entries/12c465b480be25e51c661a4e874a4f1b38d8297260f2d736c2b0c6450d74daad.html", "raw_html_sha256": "e1e41a1360af769e1437c5b89e323ab62481cd392b937d41e10901486ab3e25b", "fetched_at": "2026-07-12T02:41:21.022Z", "recordings": [ { "recording_id": "64b35f3cb1607f68510690ab8292418dd2f23bb6e816ae50100e11d58ea13411", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/74d/74dd74250e42cb9af60930c0b9c0c58d247bfa73ddc5a2311560fee8d8991abe.mp3", "archive_relative_path": "raw/audio/74d/74dd74250e42cb9af60930c0b9c0c58d247bfa73ddc5a2311560fee8d8991abe.mp3" } ] } ], "prediction": "Ntus me' we'gwi'g ta'n tujiw maljewe'g.", "reference": "Ntus maw ulte'teget natgoqwei seggw etlmesiapo'q'g." }, { "id": "mic-sent-ec24110ff40e5c45b6900543:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "If you give him/her cards, he/she will perform magic for you.", "output_text": "La'sgug ignmaj gesgmaplgigwa'lultew.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "If you give him/her cards, he/she will perform magic for you.", "mic_Latn": "La'sgug ignmaj gesgmaplgigwa'lultew." }, "canonical_ref": "entries/g/gesgmaplgigwa'latl/gesgmaplgigwa'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f22a668d84200316ccfc", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gesgmaplgigwa'latl/gesgmaplgigwa'latl.html", "entry_url": "https://mikmaqonline.org/entries/g/gesgmaplgigwa'latl/gesgmaplgigwa'latl.html", "headword": "gesgmaplgigwa'latl", "example_index": 0, "raw_html_path": "raw/entries/234c8153f1cde5f73badbf0e42a60dd70f14c565482ee21e401f6d64c110956d.html", "raw_html_sha256": "bbf22ee8d4686fbc301f9a4e09cd56806fea64bbf287b5e868ecb8d65f13adc4", "fetched_at": "2026-07-12T02:39:06.617Z", "recordings": [ { "recording_id": "a6acfa22f5671e37957e61f61dc76081a0e26bdea085d1419644be1bd8981f6f", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/450/45094d9c27487a0f11010eeaeda0dccb8477ee1d47523af15e10667e37138fdd.mp3", "archive_relative_path": "raw/audio/450/45094d9c27487a0f11010eeaeda0dccb8477ee1d47523af15e10667e37138fdd.mp3" } ] } ], "prediction": "Ge's'g ugta'latl, lugowa'toq na'te'l.", "reference": "La'sgug ignmaj gesgmaplgigwa'lultew." }, { "id": "mic-sent-ec4b7053628d63337669c3bf:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Now pulp wood is only as big around as boat push poles.", "output_text": "Palpu't nugu' pas'g tela'q st'ge gi'gamgo'ng.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Now pulp wood is only as big around as boat push poles.", "mic_Latn": "Palpu't nugu' pas'g tela'q st'ge gi'gamgo'ng." }, "canonical_ref": "entries/t/tela'q/tela'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-f6f2e264419ed87edf61", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/tela'q/tela'q.html", "entry_url": "https://mikmaqonline.org/entries/t/tela'q/tela'q.html", "headword": "tela'q", "example_index": 0, "raw_html_path": "raw/entries/9841db12cf067688c153e4224f121b3f6c5bd6aefb381689b99892db1fbd2ba1.html", "raw_html_sha256": "ca3a8748d3016897a4231da1259b0d93af157c3f56975b4a51a3c51bb8bd9321", "fetched_at": "2026-07-12T02:45:30.074Z", "recordings": [ { "recording_id": "7c66336586c8a204abe23e486b08202fc60c37cb81d21f8059d83b4d9a50bac8", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a5b/a5b238825913e359fc6cbe22dfa0210e15e72de27826cec07db0c196cc8eccd9.mp3", "archive_relative_path": "raw/audio/a5b/a5b238825913e359fc6cbe22dfa0210e15e72de27826cec07db0c196cc8eccd9.mp3" } ] } ], "prediction": "Nige' nige' pas'g te's'g ta'n tujiw gisijig pugsug.", "reference": "Palpu't nugu' pas'g tela'q st'ge gi'gamgo'ng." }, { "id": "mic-sent-ec5e3eccd0b590b1fc2aa31e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I need a short round flower pot.", "output_text": "Nuta'i toqwapsg'sit wasuego'q.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I need a short round flower pot.", "mic_Latn": "Nuta'i toqwapsg'sit wasuego'q." }, "canonical_ref": "entries/t/toqopsg'sit/toqopsg'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c7c906b3915c1312a96d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/toqopsg'sit/toqopsg'sit.html", "entry_url": "https://mikmaqonline.org/entries/t/toqopsg'sit/toqopsg'sit.html", "headword": "toqopsg'sit", "example_index": 0, "raw_html_path": "raw/entries/0f54a9c34f380bce2664bddbf08b4d43ba436e9e6c0ca6139bb90509adde0ac6.html", "raw_html_sha256": "b41521c9fda4d4abd10499fde6e0f18f5a67c85a3d1259ba422e1837a3d5b973", "fetched_at": "2026-07-12T02:46:03.857Z", "recordings": [ { "recording_id": "014acb70470e8a5421885e9711e50b6794b374771a6e2a840fd26c9dae88cc65", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/127/12795d7f35fa32b44b92f70ae790d77aec078b2af8cfb8a5f14a5e975c8005c2.mp3", "archive_relative_path": "raw/audio/127/12795d7f35fa32b44b92f70ae790d77aec078b2af8cfb8a5f14a5e975c8005c2.mp3" } ] } ], "prediction": "Amujpa nipugwelg'g na pugsug.", "reference": "Nuta'i toqwapsg'sit wasuego'q." }, { "id": "mic-sent-ec5fe86d0d9fe598d98bfe04:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My pet acts up.", "output_text": "Ntue'm amsala'sit.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My pet acts up.", "mic_Latn": "Ntue'm amsala'sit." }, "canonical_ref": "entries/a/amsala'sit/amsala'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-64725e8629727460059c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amsala'sit/amsala'sit.html", "entry_url": "https://mikmaqonline.org/entries/a/amsala'sit/amsala'sit.html", "headword": "amsala'sit", "example_index": 0, "raw_html_path": "raw/entries/c5f25f34bf34b72a5b70a8197231ef32f58960b099939f280292424670d4b574.html", "raw_html_sha256": "c4da3c3265b7ff36ea4b223b6081e0beee26296d0212ee5021d227c05a6e598c", "fetched_at": "2026-07-12T02:36:55.236Z", "recordings": [ { "recording_id": "72ca4701bbb273c21fc268f606e7f723768ff51890240d22e074b966b904f12e", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/613/6136ca52f303cce9b06c152d08d17ef44ec2191ee62168261c6010d58f7fb8bd.mp3", "archive_relative_path": "raw/audio/613/6136ca52f303cce9b06c152d08d17ef44ec2191ee62168261c6010d58f7fb8bd.mp3" } ] } ], "prediction": "Nmu'ji'j gesatg.", "reference": "Ntue'm amsala'sit." }, { "id": "mic-sent-ed092006c4ef15f1617460cd:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I've lost the baseball.", "output_text": "E'n'gaq alje'maqanaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I've lost the baseball.", "mic_Latn": "E'n'gaq alje'maqanaq." }, "canonical_ref": "entries/a/alje'maqan/alje'maqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-edeaa7ac8358b8d91053", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/alje'maqan/alje'maqan.html", "entry_url": "https://mikmaqonline.org/entries/a/alje'maqan/alje'maqan.html", "headword": "alje'maqan", "example_index": 0, "raw_html_path": "raw/entries/6b98a20f2dbf3dfb5a58eeabd012982eef3477be8e2db2456a941dedf139f0ba.html", "raw_html_sha256": "aded392f24dfba967198965d6095ce192912a790af8e17c0669ea453d7f797c7", "fetched_at": "2026-07-12T02:36:40.831Z", "recordings": [ { "recording_id": "90fe32e2e981429bb6cbabf861e13e1bc340156e31fe4e82381b0fd3722eed26", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/476/476dbf41a61693b7e27c74dcc63f81283300debd293941e0c5663c3ac4d5bdf2.mp3", "archive_relative_path": "raw/audio/476/476dbf41a61693b7e27c74dcc63f81283300debd293941e0c5663c3ac4d5bdf2.mp3" } ] } ], "prediction": "Pilei's'g na pilei.", "reference": "E'n'gaq alje'maqanaq." }, { "id": "mic-sent-ed9d92d53dc27a578f130880:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Joseph makes his kid sister cry.", "output_text": "So'sep atgitemu'latl ugwe'ji'jl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Joseph makes his kid sister cry.", "mic_Latn": "So'sep atgitemu'latl ugwe'ji'jl." }, "canonical_ref": "entries/a/atgitemu'latl/atgitemu'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-98a8f0c08e60f313d1c0", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/atgitemu'latl/atgitemu'latl.html", "entry_url": "https://mikmaqonline.org/entries/a/atgitemu'latl/atgitemu'latl.html", "headword": "atgitemu'latl", "example_index": 0, "raw_html_path": "raw/entries/8653559321fded187e7edad26d150c3acd83a74cba8905ad6facdc3af8a84192.html", "raw_html_sha256": "791afa7196e9935da33c007f90dbf45eefd29d450a2a0d33dd4c8471fdd8d92b", "fetched_at": "2026-07-12T02:37:24.641Z", "recordings": [ { "recording_id": "40f9ae4200ad3686f8fea5cffb2a886a0b211dbe40a17a35fbeaf16599d041b9", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/401/401a1516ff9fd31687f8c6d7fa3ce764830f6fbc0d0234b25f5e669f8ecb06c7.mp3", "archive_relative_path": "raw/audio/401/401a1516ff9fd31687f8c6d7fa3ce764830f6fbc0d0234b25f5e669f8ecb06c7.mp3" } ] } ], "prediction": "So'sep gesatg ugji'j.", "reference": "So'sep atgitemu'latl ugwe'ji'jl." }, { "id": "mic-sent-edc30304045b58a6b60773da:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "New potatoes are really delicious when cooked without peeling them.", "output_text": "Pilimang na mawwigapugsijig wisugwaluj mu pelgoqsasi'tigw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "New potatoes are really delicious when cooked without peeling them.", "mic_Latn": "Pilimang na mawwigapugsijig wisugwaluj mu pelgoqsasi'tigw." }, "canonical_ref": "entries/p/piliman/piliman.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c315b931e796ea7cc085", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/piliman/piliman.html", "entry_url": "https://mikmaqonline.org/entries/p/piliman/piliman.html", "headword": "piliman", "example_index": 0, "raw_html_path": "raw/entries/98f87d5934a41db114e4653a078e47da32a94c62b4b56a540b37422f81e1c76c.html", "raw_html_sha256": "bf0144e5747d2be32b7920715b22511e85e9ea327019a7349e2360ef37db4524", "fetched_at": "2026-07-12T02:43:57.743Z", "recordings": [ { "recording_id": "d2a6050fb5427aee244be7126dee8db37502fabe8a21ebc2c4a3fcd357004117", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/718/718207f4a86bdb897ce128cba260f62f4bb828550b95662ffc64b590b61bbba1.mp3", "archive_relative_path": "raw/audio/718/718207f4a86bdb897ce128cba260f62f4bb828550b95662ffc64b590b61bbba1.mp3" } ] } ], "prediction": "Pilei we'gwi'g na we'gwig ta'n tujiw gesgm'tmu'j.", "reference": "Pilimang na mawwigapugsijig wisugwaluj mu pelgoqsasi'tigw." }, { "id": "mic-sent-ee58256801c3fecbe358ffed:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "No matter how much clothing I wear, I'm chilled through, it's so cold.", "output_text": "Ta'n getu te's'g aligew nasgm, saptaqjin, telitge'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "No matter how much clothing I wear, I'm chilled through, it's so cold.", "mic_Latn": "Ta'n getu te's'g aligew nasgm, saptaqjin, telitge'g." }, "canonical_ref": "entries/s/saptaqjing/saptaqjing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e282d422f32a69daacea", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/saptaqjing/saptaqjing.html", "entry_url": "https://mikmaqonline.org/entries/s/saptaqjing/saptaqjing.html", "headword": "saptaqjing", "example_index": 0, "raw_html_path": "raw/entries/d73131fa76e22c5c1d1bd7dcfc48c384de3d315052939cb1afa286f0614733ab.html", "raw_html_sha256": "b32ab2679f4a75e61a465d498e515a2d1f058edb9ca0655f428c68caa69583e0", "fetched_at": "2026-07-12T02:44:39.343Z", "recordings": [ { "recording_id": "73894449d27e80a362abf436ca8c47e4c7d007c8a6061800581adecf9e7e98e3", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/4c9/4c95ac1ae88736562e6d44a609a66ec7171cf78ae0af9bb44b0f733f86d45049.mp3", "archive_relative_path": "raw/audio/4c9/4c95ac1ae88736562e6d44a609a66ec7171cf78ae0af9bb44b0f733f86d45049.mp3" } ] } ], "prediction": "Ta'n tujiw ta'n te's'g na'te'l, lugowaqan, te'sijig.", "reference": "Ta'n getu te's'g aligew nasgm, saptaqjin, telitge'g." }, { "id": "mic-sent-ee5f951a23f40f0d40bc8fc0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "My son likes sliding down that hill.", "output_text": "Ngwis mawigsatg nisateja'lugwej ala enmaqeg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "My son likes sliding down that hill.", "mic_Latn": "Ngwis mawigsatg nisateja'lugwej ala enmaqeg." }, "canonical_ref": "entries/m/mawigsatg/mawigsatg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-626dec6e706be9d15ad6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mawigsatg/mawigsatg.html", "entry_url": "https://mikmaqonline.org/entries/m/mawigsatg/mawigsatg.html", "headword": "mawigsatg", "example_index": 0, "raw_html_path": "raw/entries/bebc4a34511ddc38db3abde476e5194efc6d6220879fe8516c6ca76c5e29e815.html", "raw_html_sha256": "042aad9006ada02bf1cac030edfe6056ce8d4537e0f49571be2ae5e1b7bac3b6", "fetched_at": "2026-07-12T02:41:00.617Z", "recordings": [ { "recording_id": "998d0d11122b08c401ce463fa211cd8d38ea82ac1759851f36a51bead914a401", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/e6f/e6fa4afc22608754b07e9c115276c6ace22ba24e5dda6172b23241504b5591bb.mp3", "archive_relative_path": "raw/audio/e6f/e6fa4afc22608754b07e9c115276c6ace22ba24e5dda6172b23241504b5591bb.mp3" } ] } ], "prediction": "Ngwis gi's gesatg na gmu'j.", "reference": "Ngwis mawigsatg nisateja'lugwej ala enmaqeg." }, { "id": "mic-sent-eea394aa591bf1bc4d042a8b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who is that hurrying along over there?", "output_text": "Wen tana ala pemjaqala'sit?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who is that hurrying along over there?", "mic_Latn": "Wen tana ala pemjaqala'sit?" }, "canonical_ref": "entries/j/jaqala'sit/jaqala'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-de568441a899504d4efe", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jaqala'sit/jaqala'sit.html", "entry_url": "https://mikmaqonline.org/entries/j/jaqala'sit/jaqala'sit.html", "headword": "jaqala'sit", "example_index": 0, "raw_html_path": "raw/entries/64d6909ba0a2bc48aedb85b945206b64b964df76cd0b9484d4be5d0f26ea8933.html", "raw_html_sha256": "497a2da150942a99c7458898bb65a272be48bf76ce67190cbab3ccefe502d4eb", "fetched_at": "2026-07-12T02:40:14.505Z", "recordings": [ { "recording_id": "54e97d86450b1671fc2c7efdca9c1668b1be9c121a160fd498a9353345d61107", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b63/b6385c49b0cb73f00e0b92adf0e64e77c971dd478f15bfd98380f5e18c14a436.mp3", "archive_relative_path": "raw/audio/b63/b6385c49b0cb73f00e0b92adf0e64e77c971dd478f15bfd98380f5e18c14a436.mp3" } ] } ], "prediction": "Wen na ta'n te's'g?", "reference": "Wen tana ala pemjaqala'sit?" }, { "id": "mic-sent-eea9b87d83f1868fe2bb87e0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There is only one hat that is still dry.", "output_text": "Pas'g newte' a'gwesn ta'n me' niwe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There is only one hat that is still dry.", "mic_Latn": "Pas'g newte' a'gwesn ta'n me' niwe'g." }, "canonical_ref": "entries/n/niwe'g/niwe'g.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e8d1b60c411acdb31a22", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/niwe'g/niwe'g.html", "entry_url": "https://mikmaqonline.org/entries/n/niwe'g/niwe'g.html", "headword": "niwe'g", "example_index": 1, "raw_html_path": "raw/entries/b978abe8272f334a167512a6bc3c5ce547ed9438b4d1be5b59c249ba756a3b9f.html", "raw_html_sha256": "6a635fbe8394cd7b0828765a5ee27ab9e1211326128c43dbd9ad4f16cf1ad7c6", "fetched_at": "2026-07-12T02:42:39.345Z", "recordings": [ { "recording_id": "397b85646d0272e59910a46a9a40a4c9dafcbdcf2086f7b1697240e6193829a6", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a84/a841a7df95bfa09ef396478ccfa2a021b36a86c7d24f025b16f76bf859a19705.mp3", "archive_relative_path": "raw/audio/a84/a841a7df95bfa09ef396478ccfa2a021b36a86c7d24f025b16f76bf859a19705.mp3" } ] } ], "prediction": "Pas'g pas'g newte'l gmu'j gisi'g.", "reference": "Pas'g newte' a'gwesn ta'n me' niwe'g." }, { "id": "mic-sent-eec28c821b05761e2a77ee57:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is preparing the turkey so he/she can cook it.", "output_text": "Gisgaja'latl ap'tapegiejinitl glamen giswissugwalatal.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is preparing the turkey so he/she can cook it.", "mic_Latn": "Gisgaja'latl ap'tapegiejinitl glamen giswissugwalatal." }, "canonical_ref": "entries/g/gisgaja'latl/gisgaja'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8c754cc181c3bfad0e18", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gisgaja'latl/gisgaja'latl.html", "entry_url": "https://mikmaqonline.org/entries/g/gisgaja'latl/gisgaja'latl.html", "headword": "gisgaja'latl", "example_index": 0, "raw_html_path": "raw/entries/a818c66a12ca78e5fb6e373552dd4e214d2234e800b0017334ba6f389e7764d8.html", "raw_html_sha256": "64e434e5e11fa87873b23d6184b384210f2cc9ab4495ae8ee8e505445acdb7d4", "fetched_at": "2026-07-12T02:39:36.863Z", "recordings": [ { "recording_id": "5e42fde87f46b9813ebabc3fac4f2094c3eeb22f9eb86a00fad551f8595b5bd4", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/096/0965d3bb9c0643c4d2d22be307714695a82cc2e78eb9b7281c135f69d99f8f1a.mp3", "archive_relative_path": "raw/audio/096/0965d3bb9c0643c4d2d22be307714695a82cc2e78eb9b7281c135f69d99f8f1a.mp3" } ] } ], "prediction": "Pugwelg'p na gmu'ji'j gatu gisi'g.", "reference": "Gisgaja'latl ap'tapegiejinitl glamen giswissugwalatal." }, { "id": "mic-sent-eecc7fb15a44fb8192859bc1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "A fish uses its fins to steer itself in the water.", "output_text": "Nme'j e'waji ugp'sg algwi'tusin samuqwanigtug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "A fish uses its fins to steer itself in the water.", "mic_Latn": "Nme'j e'waji ugp'sg algwi'tusin samuqwanigtug." }, "canonical_ref": "entries/m/mp's/mp's.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6a0c333841b2acf1abed", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mp's/mp's.html", "entry_url": "https://mikmaqonline.org/entries/m/mp's/mp's.html", "headword": "mp's", "example_index": 0, "raw_html_path": "raw/entries/4d8cb76c5befdb23a502c8db4f1f4440aebb4136f9c5bb9ec0d8d0a077df56d0.html", "raw_html_sha256": "e6541c7ad33cdcef726aa6d609a1e4bc35d2a2c127f1671d20b12c7c31ca76fc", "fetched_at": "2026-07-12T02:36:26.255Z", "recordings": [ { "recording_id": "b51b96dc93cd354a2583a364b0f09016d07c1e8fd87bf7517af78f823e7b018d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/90d/90d9cecf9aef4d26b3f11ee2420d7264c7b2e4efc9d65d793f7bc769efefdd9a.mp3", "archive_relative_path": "raw/audio/90d/90d9cecf9aef4d26b3f11ee2420d7264c7b2e4efc9d65d793f7bc769efefdd9a.mp3" } ] } ], "prediction": "Nmu'ji'j gesatg ugta'qann.", "reference": "Nme'j e'waji ugp'sg algwi'tusin samuqwanigtug." }, { "id": "mic-sent-eecfacead3435e8414ca9ba3:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Theresa looks (shops) around for a dress.", "output_text": "Maltele's alapt'g magot.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Theresa looks (shops) around for a dress.", "mic_Latn": "Maltele's alapt'g magot." }, "canonical_ref": "entries/a/alapt'g/alapt'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-9c10a8cca3c0ceaa0977", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/alapt'g/alapt'g.html", "entry_url": "https://mikmaqonline.org/entries/a/alapt'g/alapt'g.html", "headword": "alapt'g", "example_index": 0, "raw_html_path": "raw/entries/349677af8fbafd6db76cabc377bc0993ea00a507891242741ee5b075604e51d5.html", "raw_html_sha256": "da0713cf4d03d50656b05b9ee8699999dcf8faa3f08efc1f4beed7002da228c8", "fetched_at": "2026-07-12T02:36:36.914Z", "recordings": [ { "recording_id": "ffa5f7efb79a67a157687720a3e4d31ed0a6ef651bfe6a4e2d9b3462b6ca5e6c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c67/c678250306234d6de753301b43aecc41501228250c25f92084f61113c3b37fab.mp3", "archive_relative_path": "raw/audio/c67/c678250306234d6de753301b43aecc41501228250c25f92084f61113c3b37fab.mp3" } ] } ], "prediction": "Telisa'latl ugjit ugjit.", "reference": "Maltele's alapt'g magot." }, { "id": "mic-sent-eefb142f04dfe6f2c62bdb52:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she is a bit awkward but it's his/her first time.", "output_text": "Gimu'tug awane'g pas na amgwes tellugwet.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she is a bit awkward but it's his/her first time.", "mic_Latn": "Gimu'tug awane'g pas na amgwes tellugwet." }, "canonical_ref": "entries/a/awane'g/awane'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0b3d4ce1d844340dbce6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/awane'g/awane'g.html", "entry_url": "https://mikmaqonline.org/entries/a/awane'g/awane'g.html", "headword": "awane'g", "example_index": 0, "raw_html_path": "raw/entries/c5dad43461daf7c09d22951371f1eddf24d4414b1ba8b111edea744a935ff434.html", "raw_html_sha256": "5e41a017c67b2fa9166e17b76d1e7007a0e1601d00e0e8f78446a401d2fde975", "fetched_at": "2026-07-12T02:37:28.163Z", "recordings": [ { "recording_id": "972bbb7edceaf131b682d354fde23ba5f56922dac59cd64b622aa2bd2bec2994", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/903/903383d7eab53f50b56391e82ef6dfd87210c902775091687e8737b1096a6799.mp3", "archive_relative_path": "raw/audio/903/903383d7eab53f50b56391e82ef6dfd87210c902775091687e8737b1096a6799.mp3" } ] } ], "prediction": "Gi's na gmu'jig, gatu newte'g ugjit.", "reference": "Gimu'tug awane'g pas na amgwes tellugwet." }, { "id": "mic-sent-ef3bb3c221f99e45f2f08aa8:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "One throw and the rock passes through the window.", "output_text": "Newt eleget guntew aq saputete'g tuop'ti.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "One throw and the rock passes through the window.", "mic_Latn": "Newt eleget guntew aq saputete'g tuop'ti." }, "canonical_ref": "entries/s/saputete'g/saputete'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-eaeab32299e9c1e0cb9c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/saputete'g/saputete'g.html", "entry_url": "https://mikmaqonline.org/entries/s/saputete'g/saputete'g.html", "headword": "saputete'g", "example_index": 0, "raw_html_path": "raw/entries/74fa6742d569cb36c917b467d7b2722fe075f4ecfe567a55e68e8242ef7942f1.html", "raw_html_sha256": "ad77ab91be1e8c54e294f885b534b7b85a158401e112efabc605af87632ff2ba", "fetched_at": "2026-07-12T02:44:40.547Z", "recordings": [ { "recording_id": "a711421a2a0798959756a65bb4475677fbfe2a8898d358d8c27884321ff54654", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6ab/6ab0b0fcb9092292180227f8a10d8fc2c04186debc7c36a3abe7e29e47aacd32.mp3", "archive_relative_path": "raw/audio/6ab/6ab0b0fcb9092292180227f8a10d8fc2c04186debc7c36a3abe7e29e47aacd32.mp3" } ] } ], "prediction": "Newte's'g ugjit aq gmu'j gesgm'g ta'n tujiw wenji'guomg.", "reference": "Newt eleget guntew aq saputete'g tuop'ti." }, { "id": "mic-sent-ef6cc0691f226f158c3f5679:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "What kind of bird is that flying around?", "output_text": "Talui'tut na jipji'j alaqsing?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "What kind of bird is that flying around?", "mic_Latn": "Talui'tut na jipji'j alaqsing?" }, "canonical_ref": "entries/a/alaqsing/alaqsing.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-73b6561d4dc0c50ebd7c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/alaqsing/alaqsing.html", "entry_url": "https://mikmaqonline.org/entries/a/alaqsing/alaqsing.html", "headword": "alaqsing", "example_index": 0, "raw_html_path": "raw/entries/378803b3fd8eeadf3dbc301834b0a0c18872f39ee1e6783e229069802faa922a.html", "raw_html_sha256": "45a884de469dfa78074085e4260a809d810a3c2bec9b5d17b0ffb41a27c0fa04", "fetched_at": "2026-07-12T02:36:37.214Z", "recordings": [ { "recording_id": "bad30e8f141fc0c72943ac7fc8e1e15d846720db044070103dfdaf16c2a2af3a", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/54a/54a52e15216493910255c8c42065fa027b1399a7749d3a280f727c41061edd37.mp3", "archive_relative_path": "raw/audio/54a/54a52e15216493910255c8c42065fa027b1399a7749d3a280f727c41061edd37.mp3" } ] } ], "prediction": "Ta's'g na nuji'j na ji'nm?", "reference": "Talui'tut na jipji'j alaqsing?" }, { "id": "mic-sent-efb62947fe6840515bc2a1d5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Great big tears came flowing down when the baby lost (couldn't see) his/her mother.", "output_text": "Saqpigu'nl i'tlapsglaqal pempegiaqal mijua'ji'j e'nateg uggwitl.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Great big tears came flowing down when the baby lost (couldn't see) his/her mother.", "mic_Latn": "Saqpigu'nl i'tlapsglaqal pempegiaqal mijua'ji'j e'nateg uggwitl." }, "canonical_ref": "entries/s/saqpigu'n/saqpigu'n.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ced05491f710518e5eae", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/saqpigu'n/saqpigu'n.html", "entry_url": "https://mikmaqonline.org/entries/s/saqpigu'n/saqpigu'n.html", "headword": "saqpigu'n", "example_index": 0, "raw_html_path": "raw/entries/4f8a022fd63042a16d6a18ef19ab969d832b6620fbf33069529055b25ae73d89.html", "raw_html_sha256": "ca7ee510f788b21ada8baa605eca56a2ff01d9c9db4bc9acc9fe877e9e4ac390", "fetched_at": "2026-07-12T02:44:43.459Z", "recordings": [ { "recording_id": "5c706166e14cd2aa0f81f18e5960a1626eacf7f473abff035251ad7bf81c20b2", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2f7/2f72b347eee441f1d601bfe32eb03c4aff5c972833d8fb4b330db1f436e5aec3.mp3", "archive_relative_path": "raw/audio/2f7/2f72b347eee441f1d601bfe32eb03c4aff5c972833d8fb4b330db1f436e5aec3.mp3" } ] } ], "prediction": "Pugwelg'p't'p ta'n tujiw gesatg ugji'j.", "reference": "Saqpigu'nl i'tlapsglaqal pempegiaqal mijua'ji'j e'nateg uggwitl." }, { "id": "mic-sent-f0288e261aceb4557f51fcd0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Where will the frog leave her spawn?", "output_text": "Tami sqolj tlnaqt'tew siga'law?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Where will the frog leave her spawn?", "mic_Latn": "Tami sqolj tlnaqt'tew siga'law?" }, "canonical_ref": "entries/s/siga'law/siga'law.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a85a0295e84da7d9ee44", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/siga'law/siga'law.html", "entry_url": "https://mikmaqonline.org/entries/s/siga'law/siga'law.html", "headword": "siga'law", "example_index": 0, "raw_html_path": "raw/entries/39cb5fcba6303b8afea28c4e0920945416b5c29b66a7316e7b0dc5d8a349fddd.html", "raw_html_sha256": "01b491b5ae31eebbd2fb965e93754ddbeb421c8aa3cd093067592fdcf7087680", "fetched_at": "2026-07-12T02:44:59.854Z", "recordings": [ { "recording_id": "d4234c01ef002e21a232c4cba6d7eb9b105336ed16907b4ca0e6fcd60c8883b8", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6d3/6d3547f03202e75bcf14968587eafc87e051a5df5c297e104c94bd6317b050ce.mp3", "archive_relative_path": "raw/audio/6d3/6d3547f03202e75bcf14968587eafc87e051a5df5c297e104c94bd6317b050ce.mp3" } ] } ], "prediction": "Tami we'gwisga'latl ugjitl?", "reference": "Tami sqolj tlnaqt'tew siga'law?" }, { "id": "mic-sent-f03be614fc46535e54b0e350:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Would you go and get six bundles of wheat.", "output_text": "Ge' naji'putu asugom te's'gl mawpilaqann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Would you go and get six bundles of wheat.", "mic_Latn": "Ge' naji'putu asugom te's'gl mawpilaqann." }, "canonical_ref": "entries/m/mawpilaqan/mawpilaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e5a230fb92714470c338", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mawpilaqan/mawpilaqan.html", "entry_url": "https://mikmaqonline.org/entries/m/mawpilaqan/mawpilaqan.html", "headword": "mawpilaqan", "example_index": 0, "raw_html_path": "raw/entries/dbb00667a975de122b571567a77dbced6c5df14c3f9fde3862530e62a43fb789.html", "raw_html_sha256": "eb05de3491cd332f57321a550c5a2663ede515c6b246862109d6f8923bc7cae3", "fetched_at": "2026-07-12T02:41:03.113Z", "recordings": [ { "recording_id": "8f802db0f4aa6e15b2529724786124416a83bb0cbb4945795f6b18a26db8ae49", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/911/9115967978443e7fc36c9b31b55ef8f6699e850394bef4a78a386c48f78f4286.mp3", "archive_relative_path": "raw/audio/911/9115967978443e7fc36c9b31b55ef8f6699e850394bef4a78a386c48f78f4286.mp3" } ] } ], "prediction": "Ge' gi's goqwei te's'g gmu'ji'j.", "reference": "Ge' naji'putu asugom te's'gl mawpilaqann." }, { "id": "mic-sent-f0e8d7338329fadd057340e4:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "While chasing him/her around, he/she eventually chased him/her to my home.", "output_text": "Ge's altesguaj, glapis pettesguatl nignaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "While chasing him/her around, he/she eventually chased him/her to my home.", "mic_Latn": "Ge's altesguaj, glapis pettesguatl nignaq." }, "canonical_ref": "entries/p/pettesguatl/pettesguatl.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6eb50afd80f807e673ba", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pettesguatl/pettesguatl.html", "entry_url": "https://mikmaqonline.org/entries/p/pettesguatl/pettesguatl.html", "headword": "pettesguatl", "example_index": 1, "raw_html_path": "raw/entries/ba5822d4a3798c068057b162b1396bdb45c95e257d9ceb061b4634fca706ed14.html", "raw_html_sha256": "4a1a3eaa32c42a1670934b55457f97226f4fe7b01f15ba02b153ea903c37b943", "fetched_at": "2026-07-12T02:43:49.504Z", "recordings": [ { "recording_id": "9db6957101106b42438b269c2bdde4a0e85498694ca0ce6434554c3d1b431df0", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6cf/6cfdf6b31e817c6e144ca247c0cf2595fc4f2e318132dd2dbb846cc2ceb865d4.mp3", "archive_relative_path": "raw/audio/6cf/6cfdf6b31e817c6e144ca247c0cf2595fc4f2e318132dd2dbb846cc2ceb865d4.mp3" } ] } ], "prediction": "Ta'n te's'g'p, lpa nugu' negm etlugowa'toq.", "reference": "Ge's altesguaj, glapis pettesguatl nignaq." }, { "id": "mic-sent-f0f35fdbdff8c2a0d7d12e0c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "They study at night to keep up with their work.", "output_text": "Nipgina'masultijig tepjignmnew ugtllugowaqanmuow.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "They study at night to keep up with their work.", "mic_Latn": "Nipgina'masultijig tepjignmnew ugtllugowaqanmuow." }, "canonical_ref": "entries/n/nipigina'masit/nipigina'masit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2dc77a2f810d1a3acd3e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nipigina'masit/nipigina'masit.html", "entry_url": "https://mikmaqonline.org/entries/n/nipigina'masit/nipigina'masit.html", "headword": "nipigina'masit", "example_index": 0, "raw_html_path": "raw/entries/f77aac1556c271a3810b493c20317ca9c1d777471174c4061b25905de26b71d3.html", "raw_html_sha256": "a869b66301f33a7f600d7e62864cd2e3e303522fee7eec82bebe3f595e7ed8be", "fetched_at": "2026-07-12T02:36:07.943Z", "recordings": [ { "recording_id": "3f64992cf0d90bbc0ec822be8177ef365cc282160e88c2efbb1dde3f11791295", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/b84/b84cd541092f8eb2abaa1592a9cf6f2da3200367f35c8aa95afc2f41401ca0b1.mp3", "archive_relative_path": "raw/audio/b84/b84cd541092f8eb2abaa1592a9cf6f2da3200367f35c8aa95afc2f41401ca0b1.mp3" } ] } ], "prediction": "We'gwigsitpu'tm'g ta'n tujiw negm.", "reference": "Nipgina'masultijig tepjignmnew ugtllugowaqanmuow." }, { "id": "mic-sent-f1883651a81a60c561b251d9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This is the very one I want.", "output_text": "Ul(a) eta pewalg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This is the very one I want.", "mic_Latn": "Ul(a) eta pewalg." }, "canonical_ref": "entries/e/eta/eta.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-65bfec82ca7c6e1566e6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/eta/eta.html", "entry_url": "https://mikmaqonline.org/entries/e/eta/eta.html", "headword": "eta", "example_index": 0, "raw_html_path": "raw/entries/537e97511fbb77626365e30b6f7dd183395312a6a82cfc8166f2f61262e7cea7.html", "raw_html_sha256": "7b925ecdd61dd2f31de1fc7c2bc5b5b68a4c60cd346328079991cef1531ea99e", "fetched_at": "2026-07-12T02:38:20.973Z", "recordings": [ { "recording_id": "e61b95f12dd59b2b506a10a8eced4c5c80efbdab063e51e44e6ebe95f180cbad", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a21/a212334426c025188e81ffb51d1612f37db8e5e9517177d9e736e5619d93cfbc.mp3", "archive_relative_path": "raw/audio/a21/a212334426c025188e81ffb51d1612f37db8e5e9517177d9e736e5619d93cfbc.mp3" } ] } ], "prediction": "Ula na ta'n telte'm.", "reference": "Ul(a) eta pewalg." }, { "id": "mic-sent-f1a7fc5e97e716701e90433a:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who's sail boat is that?", "output_text": "Wenewei na salpo'l?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who's sail boat is that?", "mic_Latn": "Wenewei na salpo'l?" }, "canonical_ref": "entries/s/salpo'l/salpo'l.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-001db82232751602433b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/salpo'l/salpo'l.html", "entry_url": "https://mikmaqonline.org/entries/s/salpo'l/salpo'l.html", "headword": "salpo'l", "example_index": 0, "raw_html_path": "raw/entries/9a99c206b6c50fcca6fbc4a76d2264a91d9f38a213241ec2d1991a7879f73bb6.html", "raw_html_sha256": "62a480cf87d75ef0c35888ec68ddd48a377f6e2dc7cf312204b374379d5490c9", "fetched_at": "2026-07-12T02:44:34.721Z", "recordings": [ { "recording_id": "869d7b10697ecab167e86527f3dde21f97f4b0ce486a7b9c7af0e5b1fd10aa8c", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/a35/a35d9ccde58686d593bcbfea548bc07dc36755c2f6b8bf0cdb6485fe0b12cf51.mp3", "archive_relative_path": "raw/audio/a35/a35d9ccde58686d593bcbfea548bc07dc36755c2f6b8bf0cdb6485fe0b12cf51.mp3" } ] } ], "prediction": "Wen na wi'gwi'g na?", "reference": "Wenewei na salpo'l?" }, { "id": "mic-sent-f1c76c78989720ce99a2a0d0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That man works so quickly, hire him right away.", "output_text": "Teljaqallugwet na ji'nm, smtug agase'wa'lug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That man works so quickly, hire him right away.", "mic_Latn": "Teljaqallugwet na ji'nm, smtug agase'wa'lug." }, "canonical_ref": "entries/j/jaqalilugwet/jaqalilugwet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3631ca610aaa42f347cd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jaqalilugwet/jaqalilugwet.html", "entry_url": "https://mikmaqonline.org/entries/j/jaqalilugwet/jaqalilugwet.html", "headword": "jaqalilugwet", "example_index": 0, "raw_html_path": "raw/entries/e3d79a7188fdf2b18cdab4bbec35fda98ec61ad686f93777fe57b77a83c3d6d8.html", "raw_html_sha256": "4d3578ac6cd584db4394ef7fb106bd7db688a548ce695a643d7f9b373bb0d480", "fetched_at": "2026-07-12T02:40:14.802Z", "recordings": [ { "recording_id": "07f6c7b00038f2ecd4739e47cd94eb24e92af91e707ada3f282383096c6ca757", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/27d/27d6e5e178163c0ea04d22a8b8a31d1385a0bf4a959a873647e34bcdb6b8e379.mp3", "archive_relative_path": "raw/audio/27d/27d6e5e178163c0ea04d22a8b8a31d1385a0bf4a959a873647e34bcdb6b8e379.mp3" } ] } ], "prediction": "Wesgowa'sit na ji'nm, gi's gi'l.", "reference": "Teljaqallugwet na ji'nm, smtug agase'wa'lug." }, { "id": "mic-sent-f23338285215dbaa8128ed60:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Is there anyone here that knows how to play the horn?", "output_text": "Eig wen tet ta'n nata'te'g pipugwaqan?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Is there anyone here that knows how to play the horn?", "mic_Latn": "Eig wen tet ta'n nata'te'g pipugwaqan?" }, "canonical_ref": "entries/p/pipugwaqan/pipugwaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6496694494d8872ee24f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pipugwaqan/pipugwaqan.html", "entry_url": "https://mikmaqonline.org/entries/p/pipugwaqan/pipugwaqan.html", "headword": "pipugwaqan", "example_index": 0, "raw_html_path": "raw/entries/8416e4be13146a3619c14a3642915ab5fafc56875551c6ba8a02b6411ceb3452.html", "raw_html_sha256": "f524d72c4250abe74e8cd87773a38da9e6f4b28876ee3b3de25fa5b89d6cecd6", "fetched_at": "2026-07-12T02:44:00.769Z", "recordings": [ { "recording_id": "b7cd447680eaee45d1c131be1b755a7767b8d10db933da36b8653635d9082aae", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/eed/eed23de6ce6c7cbe529861700bf72aa8c9f124a1d9b9d33598de378bf8ad71b3.mp3", "archive_relative_path": "raw/audio/eed/eed23de6ce6c7cbe529861700bf72aa8c9f124a1d9b9d33598de378bf8ad71b3.mp3" } ] } ], "prediction": "Gi's gi'l na ula ji'nm ta'n tujiw gmu'j?", "reference": "Eig wen tet ta'n nata'te'g pipugwaqan?" }, { "id": "mic-sent-f29cf8925fdf425bd4ee661e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That little girl speaks Mi'gmaw well.", "output_text": "Welinnui'sit na ala e'pite'ji'j.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That little girl speaks Mi'gmaw well.", "mic_Latn": "Welinnui'sit na ala e'pite'ji'j." }, "canonical_ref": "entries/n/nnui'sit/nnui'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-87a408eb11ec3d2420ec", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nnui'sit/nnui'sit.html", "entry_url": "https://mikmaqonline.org/entries/n/nnui'sit/nnui'sit.html", "headword": "nnui'sit", "example_index": 0, "raw_html_path": "raw/entries/0d70d320d99300bd3e51ff8302639e8af7169389ef4267128d4774ef12ab06f5.html", "raw_html_sha256": "5ace1f9d0b4d7ce3183cd95001352c793b70ae819dbe74c494709408836885eb", "fetched_at": "2026-07-12T02:42:41.459Z", "recordings": [ { "recording_id": "6dd0897d23d46066c7f2174723e4523a1c4f69bdefab53b5b71cd5732418f3e3", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/52b/52bc75094597f4592678854d50d2611436ba7c95fe25123e5a675e2f8cf1bdff.mp3", "archive_relative_path": "raw/audio/52b/52bc75094597f4592678854d50d2611436ba7c95fe25123e5a675e2f8cf1bdff.mp3" } ] } ], "prediction": "Ala na'te'ji'j mijua'sit Mi'gmaw.", "reference": "Welinnui'sit na ala e'pite'ji'j." }, { "id": "mic-sent-f310aa7da8c8d19a92a30f77:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The sheet is flat after it is spread out.", "output_text": "Sasqapit naqsun gislega'luj.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The sheet is flat after it is spread out.", "mic_Latn": "Sasqapit naqsun gislega'luj." }, "canonical_ref": "entries/s/sasqapit/sasqapit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-56ead44267505d13f1b3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sasqapit/sasqapit.html", "entry_url": "https://mikmaqonline.org/entries/s/sasqapit/sasqapit.html", "headword": "sasqapit", "example_index": 0, "raw_html_path": "raw/entries/3005d738b244363a979de06bb10f1c20d3b03f1035b5c3cae2083b317362dba8.html", "raw_html_sha256": "f42e3d2df255e7cdc55aaaad19f71c2f286f9b6be2fad2e646df07f0cb0c8bdd", "fetched_at": "2026-07-12T02:44:46.062Z", "recordings": [ { "recording_id": "2a9e247bb15db86b4df0b8a16acddc9b77d2c8628c50ea6d6a919202a7016a88", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/70d/70dae928c69db8914fb9ccd0636c1bf2c5e546b0276be2f5964993265e266db5.mp3", "archive_relative_path": "raw/audio/70d/70dae928c69db8914fb9ccd0636c1bf2c5e546b0276be2f5964993265e266db5.mp3" } ] } ], "prediction": "Pilei'g na lpa we'gwi'g ta'n tujiw pas'g.", "reference": "Sasqapit naqsun gislega'luj." }, { "id": "mic-sent-f3eb3ea89d84f212fb8c15c2:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she broke the tail off the statue when he/she dropped it.", "output_text": "Lpa temaluetesmatl nnuoqta'wl petnisegeteg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she broke the tail off the statue when he/she dropped it.", "mic_Latn": "Lpa temaluetesmatl nnuoqta'wl petnisegeteg." }, "canonical_ref": "entries/t/temalueitesmatl/temalueitesmatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6e460ac93e019d9a71e6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/temalueitesmatl/temalueitesmatl.html", "entry_url": "https://mikmaqonline.org/entries/t/temalueitesmatl/temalueitesmatl.html", "headword": "temalueitesmatl", "example_index": 0, "raw_html_path": "raw/entries/9905f94859af962f85c88bfcd17e7eea438334be199d12f3135b6bc85255d60e.html", "raw_html_sha256": "6ec0d88a2f7b35a384a23bf8dd080fc933ee160d18bea042ae15e4074c133908", "fetched_at": "2026-07-12T02:45:36.639Z", "recordings": [ { "recording_id": "306cff6d7d575eba7af86e5a33196419b7b3d9af8fc631cdf51d297933a43a0a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cbf/cbf5dd502305e4d69aa7134546084973093816042a1e9dd61588779c6fb6b438.mp3", "archive_relative_path": "raw/audio/cbf/cbf5dd502305e4d69aa7134546084973093816042a1e9dd61588779c6fb6b438.mp3" } ] } ], "prediction": "Pugwelg'p na ugjit ta'n tujiw gesatg.", "reference": "Lpa temaluetesmatl nnuoqta'wl petnisegeteg." }, { "id": "mic-sent-f46b79ec6b87b9837cd46f64:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she wants to eat that bannock so much, he/she is salivating.", "output_text": "Teligtutg na lusgnign lpa pene'sugwa't.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she wants to eat that bannock so much, he/she is salivating.", "mic_Latn": "Teligtutg na lusgnign lpa pene'sugwa't." }, "canonical_ref": "entries/g/getutg/getutg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-c236c56dd3de5adcbd93", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/getutg/getutg.html", "entry_url": "https://mikmaqonline.org/entries/g/getutg/getutg.html", "headword": "getutg", "example_index": 0, "raw_html_path": "raw/entries/a310fbf2eb3d43a1aa8143442fa992f300ec3640a76a4701ec8dc8f36a76726d.html", "raw_html_sha256": "90c1a585f261a0013b70a793be084e5b8c71deadd77720f8c919264fba4bca03", "fetched_at": "2026-07-12T02:39:25.494Z", "recordings": [ { "recording_id": "74615c3bac1cd593282ede7b2051abd4dfcadea75811c328b27e6fb4d29feaf1", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/99a/99acef5f9fc5b4d8c82b95f72933e9a02df1a67419d7a4aac98145678ffe7431.mp3", "archive_relative_path": "raw/audio/99a/99acef5f9fc5b4d8c82b95f72933e9a02df1a67419d7a4aac98145678ffe7431.mp3" } ] } ], "prediction": "Te's gesatg na gmu'ji'j, lpa gisi'g.", "reference": "Teligtutg na lusgnign lpa pene'sugwa't." }, { "id": "mic-sent-f46c5961d3e6413480f4b1de:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "This (item) placed here, where does is go?", "output_text": "U't eteg, tami eliaq?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "This (item) placed here, where does is go?", "mic_Latn": "U't eteg, tami eliaq?" }, "canonical_ref": "entries/u/u't/u't.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-997b6ffa882f3050ff3e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/u't/u't.html", "entry_url": "https://mikmaqonline.org/entries/u/u't/u't.html", "headword": "u't", "example_index": 0, "raw_html_path": "raw/entries/61fdabf4a9c5c474f4795fd735a83c2b0c2e5f2ae2e5d2a1b2b1a573d4515306.html", "raw_html_sha256": "ffc43f928ea4576d50533891f48d04b775ef489e99d23ac8fac15e537c84a38e", "fetched_at": "2026-07-12T02:46:27.586Z", "recordings": [ { "recording_id": "52436e101757a6d1b04330257f4f995fc890ef458a2fc3451ec27947a9efe05b", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c7b/c7b907a35cb7d60c56c4942f8f88f575de904d4f51aa1df64314fc246aa0e129.mp3", "archive_relative_path": "raw/audio/c7b/c7b907a35cb7d60c56c4942f8f88f575de904d4f51aa1df64314fc246aa0e129.mp3" } ] } ], "prediction": "Ula tet, ta'n goqwei?", "reference": "U't eteg, tami eliaq?" }, { "id": "mic-sent-f5557d7a70c0fff3edf8cb32:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Who was swinging that boy around?", "output_text": "Wen gi's giwto'qopega'latl na l'pa'tujl?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Who was swinging that boy around?", "mic_Latn": "Wen gi's giwto'qopega'latl na l'pa'tujl?" }, "canonical_ref": "entries/g/giwto'qopega'latl/giwto'qopega'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a6696f54304a40c3ae32", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/giwto'qopega'latl/giwto'qopega'latl.html", "entry_url": "https://mikmaqonline.org/entries/g/giwto'qopega'latl/giwto'qopega'latl.html", "headword": "giwto'qopega'latl", "example_index": 0, "raw_html_path": "raw/entries/ecccfd6c6b8bc7431fd76676260fe667691488b104ea58d38120e8676ef050f2.html", "raw_html_sha256": "51d9c3607469194fd6c25f68597344da33b679dbb1120817b0abdaba921ce3ed", "fetched_at": "2026-07-12T02:39:47.322Z", "recordings": [ { "recording_id": "013b2f2911f246830f909c666a507f1ccfd212987afe88968ec563d402e646a3", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/aa3/aa3da22c1854b23df8a9f46fd89701df04150292ccdde5594ebe1bca406405f1.mp3", "archive_relative_path": "raw/audio/aa3/aa3da22c1854b23df8a9f46fd89701df04150292ccdde5594ebe1bca406405f1.mp3" } ] } ], "prediction": "Wen gi's na lpa lpa'tuj?", "reference": "Wen gi's giwto'qopega'latl na l'pa'tujl?" }, { "id": "mic-sent-f57d6e84fcc50238b42361a9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has written a good story.", "output_text": "Gelulg a'tugwaqan gis wi'g'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has written a good story.", "mic_Latn": "Gelulg a'tugwaqan gis wi'g'g." }, "canonical_ref": "entries/a/a'tugwaqan/a'tugwaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-87060fa1d97cdd4b2641", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/a'tugwaqan/a'tugwaqan.html", "entry_url": "https://mikmaqonline.org/entries/a/a'tugwaqan/a'tugwaqan.html", "headword": "a'tugwaqan", "example_index": 0, "raw_html_path": "raw/entries/cec266d345c9136a65ee58a277641c63c37e9f89c58821279dc7271611423ac6.html", "raw_html_sha256": "c0248bb14a80e1b3f8a207d216379b4c72e230d90340f1215c48095dc2d1b87e", "fetched_at": "2026-07-12T02:37:27.257Z", "recordings": [ { "recording_id": "6fba8ec386515b46d693bbf3e57ab50d65b3dae9411d9d9befec8ad663b5c5e5", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d7d/d7d31b5ff8d0dd9e40990944fadf1055bb9aa19e077e817db70c05d33f6d3732.mp3", "archive_relative_path": "raw/audio/d7d/d7d31b5ff8d0dd9e40990944fadf1055bb9aa19e077e817db70c05d33f6d3732.mp3" } ] } ], "prediction": "We'gwi'g na wi'gatign.", "reference": "Gelulg a'tugwaqan gis wi'g'g." }, { "id": "mic-sent-f599915f74ebc15cf10de829:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "They must be sweethearts, they're holding each other so tight.", "output_text": "Amuj na plgoqq, telseggntijig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "They must be sweethearts, they're holding each other so tight.", "mic_Latn": "Amuj na plgoqq, telseggntijig." }, "canonical_ref": "entries/p/plgoq/plgoq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d930eafc30499c33755c", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/plgoq/plgoq.html", "entry_url": "https://mikmaqonline.org/entries/p/plgoq/plgoq.html", "headword": "plgoq", "example_index": 0, "raw_html_path": "raw/entries/d9e822bfd320de51936b4c145343f988f381c01657ac43c2fc54d292e018cc6c.html", "raw_html_sha256": "5238afc39fb4e1886b8633be16ddcb7e8d2d753e11a04d29540b69542851c519", "fetched_at": "2026-07-12T02:44:12.610Z", "recordings": [ { "recording_id": "d9c6cb0bae35f49bf7e5b3a8aa5db6a0ff5f94e3ac339302e752429a6706692a", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/61b/61b7f91f0c818108d9f2bd863d82bb2688361cbf59fb43415f6f3c32a2c23fb9.mp3", "archive_relative_path": "raw/audio/61b/61b7f91f0c818108d9f2bd863d82bb2688361cbf59fb43415f6f3c32a2c23fb9.mp3" } ] } ], "prediction": "Amujpa amujpa'toq, telte'gigtug.", "reference": "Amuj na plgoqq, telseggntijig." }, { "id": "mic-sent-f614d458734adc3b8693763b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I don't know any person with supernatural powers.", "output_text": "Mu ni'n nenuaq mi'gmuessu.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I don't know any person with supernatural powers.", "mic_Latn": "Mu ni'n nenuaq mi'gmuessu." }, "canonical_ref": "entries/m/mi'gmuessu/mi'gmuessu.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-2bc5f714ba45da40c10e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mi'gmuessu/mi'gmuessu.html", "entry_url": "https://mikmaqonline.org/entries/m/mi'gmuessu/mi'gmuessu.html", "headword": "mi'gmuessu", "example_index": 0, "raw_html_path": "raw/entries/8b1d2ef32772e0c32b5e94b1e30171ca890b91bbee8855c13b4c0cc547c89351.html", "raw_html_sha256": "a959d0b69913e8b97bd91147069fa94cbd4963ce1aae7905cddc580f76dbe7f2", "fetched_at": "2026-07-12T02:41:33.244Z", "recordings": [ { "recording_id": "f7c494067d7cda1449640a23b25031c7ee1ed02a92cbc58a7852f8606c027d2d", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/eb5/eb5414e70c2cff6be88b02119a53fd29ab3540eae583ae1c76bd546d65cf720e.mp3", "archive_relative_path": "raw/audio/eb5/eb5414e70c2cff6be88b02119a53fd29ab3540eae583ae1c76bd546d65cf720e.mp3" } ] } ], "prediction": "Mu ni'n te's'g ta'n tujiw wi'gwi'jig.", "reference": "Mu ni'n nenuaq mi'gmuessu." }, { "id": "mic-sent-f653831b346fc2199f91b4fc:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/She is stuck in the corner.", "output_text": "Amjimoqwa'sit gejigiaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/She is stuck in the corner.", "mic_Latn": "Amjimoqwa'sit gejigiaq." }, "canonical_ref": "entries/a/amjimoqwa'sit/amjimoqwa'sit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-3be0474448d11b8e05c3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amjimoqwa'sit/amjimoqwa'sit.html", "entry_url": "https://mikmaqonline.org/entries/a/amjimoqwa'sit/amjimoqwa'sit.html", "headword": "amjimoqwa'sit", "example_index": 0, "raw_html_path": "raw/entries/edc41c1d4362aed592a4afc6a96ba6d51d66b20844fc37cf17606332fb6c1b1b.html", "raw_html_sha256": "323072fbd6dd8e8a850eb679b5b27fafa364a09852be87b992cbf21eb9cde4f7", "fetched_at": "2026-07-12T02:36:53.938Z", "recordings": [ { "recording_id": "81447821a1634d118df8d6caa37c87806fe71cf50c2419f5b0251153686a8f03", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d0e/d0e1b3edb855b7ed8653bdc06bf22b43019410296cdc0a51849d95f152096bc5.mp3", "archive_relative_path": "raw/audio/d0e/d0e1b3edb855b7ed8653bdc06bf22b43019410296cdc0a51849d95f152096bc5.mp3" } ] } ], "prediction": "We'gwi'g e'pite'g.", "reference": "Amjimoqwa'sit gejigiaq." }, { "id": "mic-sent-f6e20505871d2a6576e6a4fa:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "They will start singing soon, but first they are waiting for this person to finish speaking.", "output_text": "Pujig poqjigtapegia'tijig, pas'g pe'l esgmala'titl ula gaqewo'gwenin.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "They will start singing soon, but first they are waiting for this person to finish speaking.", "mic_Latn": "Pujig poqjigtapegia'tijig, pas'g pe'l esgmala'titl ula gaqewo'gwenin." }, "canonical_ref": "entries/p/poqjigtapegiet/poqjigtapegiet.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-be24c5956df1c0a0e5fd", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/poqjigtapegiet/poqjigtapegiet.html", "entry_url": "https://mikmaqonline.org/entries/p/poqjigtapegiet/poqjigtapegiet.html", "headword": "poqjigtapegiet", "example_index": 0, "raw_html_path": "raw/entries/1aa19a0469bc17b0768db6f5a4dd991c3147018e4067d5d1a9784148aee23922.html", "raw_html_sha256": "ffecfedfa1778372aeadd2c6dc26065011855bcb6d76f5c52f881da76401fc19", "fetched_at": "2026-07-12T02:44:14.333Z", "recordings": [ { "recording_id": "d9b069ed3bcfba19fba86467712ccdb952093610078ca2fad093677c1a81d334", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8d3/8d382013b88181127a8f089c265cfd588eeee4c3bb24057a9f78ffbf78c3ad45.mp3", "archive_relative_path": "raw/audio/8d3/8d382013b88181127a8f089c265cfd588eeee4c3bb24057a9f78ffbf78c3ad45.mp3" } ] } ], "prediction": "Pugwelg'p'tijig, gatu gatu gisgm'g na ula ji'nm gesatg.", "reference": "Pujig poqjigtapegia'tijig, pas'g pe'l esgmala'titl ula gaqewo'gwenin." }, { "id": "mic-sent-f6f640faebd090ca037ec7e7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I don't want to make use of that cain.", "output_text": "Mu getu' wetmo'tmu na aptu'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I don't want to make use of that cain.", "mic_Latn": "Mu getu' wetmo'tmu na aptu'n." }, "canonical_ref": "entries/w/wetmo'tg/wetmo'tg.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-14293463779f273fa887", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/wetmo'tg/wetmo'tg.html", "entry_url": "https://mikmaqonline.org/entries/w/wetmo'tg/wetmo'tg.html", "headword": "wetmo'tg", "example_index": 0, "raw_html_path": "raw/entries/b955677dddcdddf6d45aabe0559244c8fde152e42ae73f21cfb3c215bc5222ac.html", "raw_html_sha256": "732d6c40d9e2e0dc3f8f9f5bc137e349c393e18cc2fea756176d5cfd39f3c1b8", "fetched_at": "2026-07-12T02:47:25.082Z", "recordings": [ { "recording_id": "20fa388a19910defefb4391c8c389b25ef728b37a852a5f14fdac3e2cb39e495", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/9c6/9c667b2a712cf5c843797a61c36e5c37285fba06169871f0e8b913c2b3aaf987.mp3", "archive_relative_path": "raw/audio/9c6/9c667b2a712cf5c843797a61c36e5c37285fba06169871f0e8b913c2b3aaf987.mp3" } ] } ], "prediction": "Mu ni'n ge's na gmu'j.", "reference": "Mu getu' wetmo'tmu na aptu'n." }, { "id": "mic-sent-f7a947be6f1594f650591490:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I know that he/she is angry, I can hear him/her sounding off.", "output_text": "Geji'g wegai'g, lpa nutaq metewilua't.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I know that he/she is angry, I can hear him/her sounding off.", "mic_Latn": "Geji'g wegai'g, lpa nutaq metewilua't." }, "canonical_ref": "entries/m/metewilua't/metewilua't.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0ac12b7e0a2040b9b669", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/metewilua't/metewilua't.html", "entry_url": "https://mikmaqonline.org/entries/m/metewilua't/metewilua't.html", "headword": "metewilua't", "example_index": 0, "raw_html_path": "raw/entries/a8f18534b92a310823e995dea921c24f929f67c17e46804bf6bc9e0e9bcbbe11.html", "raw_html_sha256": "de90d22885535d6198eb8475f72a78632758730c76c725d0e029f65b05067728", "fetched_at": "2026-07-12T02:41:26.893Z", "recordings": [ { "recording_id": "93370283c43928364491fedfc575333790ea34b1c6d4792a8e58eae3acfd3180", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/c67/c67dd862602d73a7077806461d77ddc44db376b33e48371157f222f3f63de00b.mp3", "archive_relative_path": "raw/audio/c67/c67dd862602d73a7077806461d77ddc44db376b33e48371157f222f3f63de00b.mp3" } ] } ], "prediction": "Ge' gi'l ge's'g, na'te'l etlmisga'toq.", "reference": "Geji'g wegai'g, lpa nutaq metewilua't." }, { "id": "mic-sent-f85845cf7c861752d90f9518:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I saw their boat, it was going up river", "output_text": "Nemitaqapneg ugtuluow, pempi'tawa's'g'p.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I saw their boat, it was going up river", "mic_Latn": "Nemitaqapneg ugtuluow, pempi'tawa's'g'p." }, "canonical_ref": "entries/p/pi'tawa's'g/pi'tawa's'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-eb30d0c43f7f2455113e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pi'tawa's'g/pi'tawa's'g.html", "entry_url": "https://mikmaqonline.org/entries/p/pi'tawa's'g/pi'tawa's'g.html", "headword": "pi'tawa's'g", "example_index": 0, "raw_html_path": "raw/entries/4cda560d2433b201448651272e7a9299c3c6c3d3d1f2f2495875250088845f79.html", "raw_html_sha256": "f7d733f1632758e22aa996960e785d6e7c629aa0109e0a55654ff8fb7afb59e6", "fetched_at": "2026-07-12T02:44:06.887Z", "recordings": [ { "recording_id": "ff1695861d4b0ba73bb8a03de1516b75531b39fea92c97b401e20656d73a7262", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/82e/82eb916784a8a177750e9e5c7cfa4255f0bb0892a8bc24d4159bf95831b94f6a.mp3", "archive_relative_path": "raw/audio/82e/82eb916784a8a177750e9e5c7cfa4255f0bb0892a8bc24d4159bf95831b94f6a.mp3" } ] } ], "prediction": "Nemi'g'p na wi'gatig, lpa gisijig.", "reference": "Nemitaqapneg ugtuluow, pempi'tawa's'g'p." }, { "id": "mic-sent-f87b7b5f8dbef11d3367f396:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The woman rests her child.", "output_text": "E'pit atlasmu'latl unjann.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The woman rests her child.", "mic_Latn": "E'pit atlasmu'latl unjann." }, "canonical_ref": "entries/a/atlasmu'latl/atlasmu'latl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-5c417225156b25b3ecbb", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/atlasmu'latl/atlasmu'latl.html", "entry_url": "https://mikmaqonline.org/entries/a/atlasmu'latl/atlasmu'latl.html", "headword": "atlasmu'latl", "example_index": 0, "raw_html_path": "raw/entries/c3676f593f81c94486320f4142e0dc437e19ce4c3d45c46621289ccfb2e7c72b.html", "raw_html_sha256": "f0af699667c39ae423f968117adb99b1565cf7fa5c8a0468b47ab2bc8b33b131", "fetched_at": "2026-07-12T02:37:25.547Z", "recordings": [ { "recording_id": "97e90abc6dc958c10646eb13633d25415188481d66e41799a7d8dd24cb97b7f0", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/336/3360fbc24cb1b03bc6f5932547ab35ca93e33feb221ee2fabe8ac39c562ad3d9.mp3", "archive_relative_path": "raw/audio/336/3360fbc24cb1b03bc6f5932547ab35ca93e33feb221ee2fabe8ac39c562ad3d9.mp3" } ] } ], "prediction": "E'pite'ji'j na'te'l ugjitl.", "reference": "E'pit atlasmu'latl unjann." }, { "id": "mic-sent-f88e4aef95b5b5eaae661a96:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The Savior is often mentioned in prayers.", "output_text": "Ewi'tut gaqi'sg a'sutmaqanigtug westawu'lgw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The Savior is often mentioned in prayers.", "mic_Latn": "Ewi'tut gaqi'sg a'sutmaqanigtug westawu'lgw." }, "canonical_ref": "entries/w/westawu'lgw/westawu'lgw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-1ab1d883197594af4606", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/w/westawu'lgw/westawu'lgw.html", "entry_url": "https://mikmaqonline.org/entries/w/westawu'lgw/westawu'lgw.html", "headword": "westawu'lgw", "example_index": 0, "raw_html_path": "raw/entries/d0c5fb10c92819bcbcdf70bfbcecf1bbd802f645fe31429447aa0ad75092d737.html", "raw_html_sha256": "56c9181a6c10134fc4547a65162e734e6674ac029eb5013d9e2e00dd03e97076", "fetched_at": "2026-07-12T02:47:20.858Z", "recordings": [ { "recording_id": "a0bc9dcae6de0db917612e1368ffcfcf9f1216840a0269f46a324190deb193af", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/d83/d83bdd903f13fde6fb91ff8b395f88c13e0beb21ce6cae0e1c16fac50e6df18e.mp3", "archive_relative_path": "raw/audio/d83/d83bdd903f13fde6fb91ff8b395f88c13e0beb21ce6cae0e1c16fac50e6df18e.mp3" } ] } ], "prediction": "Te's'g ta'n tujiw nugu' wenji'guomgigtug.", "reference": "Ewi'tut gaqi'sg a'sutmaqanigtug westawu'lgw." }, { "id": "mic-sent-f8ace51d93a0206e8f6e7077:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The knitting you have done is nice.", "output_text": "Gelu'lg elisgnuaqan gisa'tu'n.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The knitting you have done is nice.", "mic_Latn": "Gelu'lg elisgnuaqan gisa'tu'n." }, "canonical_ref": "entries/e/elisgnuaqan/elisgnuaqan.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-e181b45bb5ab5146263b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/elisgnuaqan/elisgnuaqan.html", "entry_url": "https://mikmaqonline.org/entries/e/elisgnuaqan/elisgnuaqan.html", "headword": "elisgnuaqan", "example_index": 0, "raw_html_path": "raw/entries/c43bc3a965a16a9ed0f00f2fb4a2248aeeb86dbfab145366ea79d3a5adb3fb14.html", "raw_html_sha256": "35151ffd9e85a2e0693b7b801142bf1577d8fe89f19e59a08362ef915ca55877", "fetched_at": "2026-07-12T02:37:46.715Z", "recordings": [ { "recording_id": "bc711aaae9d8d0d44c42a90a2f3b3aefb05f935333a7ba560cf18e4aa734d116", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/31e/31eb21dfb5144a50495cdd7da505fce863019b7282ef8424b865a658d2a44011.mp3", "archive_relative_path": "raw/audio/31e/31eb21dfb5144a50495cdd7da505fce863019b7282ef8424b865a658d2a44011.mp3" } ] } ], "prediction": "We'gwi'g'p ta'n tujiw ugjit.", "reference": "Gelu'lg elisgnuaqan gisa'tu'n." }, { "id": "mic-sent-f8b47c0e349a8283ad3d6bad:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "There are many spirits around a native community.", "output_text": "Mjijaqamij na pugwelg ale'g Nnue'gatig.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "There are many spirits around a native community.", "mic_Latn": "Mjijaqamij na pugwelg ale'g Nnue'gatig." }, "canonical_ref": "entries/m/mjijaqamij/mjijaqamij.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6c95d290621d0c55aa6e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/mjijaqamij/mjijaqamij.html", "entry_url": "https://mikmaqonline.org/entries/m/mjijaqamij/mjijaqamij.html", "headword": "mjijaqamij", "example_index": 0, "raw_html_path": "raw/entries/93885a885d8d80614de1df10f93a51ff1405336e4aca5406833dd5a7c6091678.html", "raw_html_sha256": "9db8750ae2f98fb643f290b760556b28673efaf18417be5c08624ed177678b6e", "fetched_at": "2026-07-12T02:41:42.712Z", "recordings": [ { "recording_id": "af370291537a7b32df5506ca3c00f157aaadb3365f990a62c3b926c0a66c7adc", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/8c6/8c616d47c9e5ed55a925c8db71d6ad8162c0d3978c0fb708c3647e3c79039ad9.mp3", "archive_relative_path": "raw/audio/8c6/8c616d47c9e5ed55a925c8db71d6ad8162c0d3978c0fb708c3647e3c79039ad9.mp3" } ] } ], "prediction": "Pugwelg'p na gmu'ji'jig ta'n tujiw wi'gwigtug.", "reference": "Mjijaqamij na pugwelg ale'g Nnue'gatig." }, { "id": "mic-sent-f9441a73881b92eb0c5af0e6:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Count your fingers.", "output_text": "Gite'n ugtluignn.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Count your fingers.", "mic_Latn": "Gite'n ugtluignn." }, "canonical_ref": "entries/u/ugtluign/ugtluign.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8c0547fbc6d68d05122e", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/u/ugtluign/ugtluign.html", "entry_url": "https://mikmaqonline.org/entries/u/ugtluign/ugtluign.html", "headword": "ugtluign", "example_index": 0, "raw_html_path": "raw/entries/217157bcf7c1b60cd534dec7c16ab0212c7f6d6e917864ea7ae24d7722d29516.html", "raw_html_sha256": "f780173a68a74c9b3b55d765446fa9842885eaf30428011a329bc03ab2b3a15f", "fetched_at": "2026-07-12T02:46:18.544Z", "recordings": [ { "recording_id": "a1a57c679b5cfda1f91a7d9939a5f5a11fb8ff784fdfb10bebd43e2332671416", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/6a0/6a05f3993560429c9a15e15c8e50cb581c62e3e81ae0b2f9cbe3ca0b333cfa02.mp3", "archive_relative_path": "raw/audio/6a0/6a05f3993560429c9a15e15c8e50cb581c62e3e81ae0b2f9cbe3ca0b333cfa02.mp3" } ] } ], "prediction": "Pugwelga'toq ugjit.", "reference": "Gite'n ugtluignn." }, { "id": "mic-sent-f966eeca7caba2f166a0d822:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "That barrel has too large of an opening, we can't use it.", "output_text": "Wesammaqalqasit na malige'w, ma gisie'wagw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "That barrel has too large of an opening, we can't use it.", "mic_Latn": "Wesammaqalqasit na malige'w, ma gisie'wagw." }, "canonical_ref": "entries/m/maqalqasit/maqalqasit.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-de2011e84152c9b22f64", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/maqalqasit/maqalqasit.html", "entry_url": "https://mikmaqonline.org/entries/m/maqalqasit/maqalqasit.html", "headword": "maqalqasit", "example_index": 0, "raw_html_path": "raw/entries/2f8b2dfee32c90368ed1d6092d38d22aa7993fc13069e9e9c12c5454217249e1.html", "raw_html_sha256": "3e03447bd4aa7111287b0f4c258aa6ffa387672296c6e6c8b142b0d741bac2c0", "fetched_at": "2026-07-12T02:40:48.337Z", "recordings": [ { "recording_id": "4bee79dba3f63ca1d0230be3ff3886cee4cecd9867b7872f8e0c565312fdecc7", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/2c8/2c8cddbc03891417e5e559c9057b237db7dceba2a8f69e986f8df0a00ab6b649.mp3", "archive_relative_path": "raw/audio/2c8/2c8cddbc03891417e5e559c9057b237db7dceba2a8f69e986f8df0a00ab6b649.mp3" } ] } ], "prediction": "We'ga'toq na gmu'ji'j, ma' nugu' negm.", "reference": "Wesammaqalqasit na malige'w, ma gisie'wagw." }, { "id": "mic-sent-fa425f99b90707941283737e:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "How many racers are you waiting for?", "output_text": "Ta'sijig igatne'suinug esgmaljig?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "How many racers are you waiting for?", "mic_Latn": "Ta'sijig igatne'suinug esgmaljig?" }, "canonical_ref": "entries/i/igatne'suinu/igatne'suinu.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-0446e96a8c610fc930c2", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/i/igatne'suinu/igatne'suinu.html", "entry_url": "https://mikmaqonline.org/entries/i/igatne'suinu/igatne'suinu.html", "headword": "igatne'suinu", "example_index": 0, "raw_html_path": "raw/entries/f2da5a7f052127c373cf06ff33112c2e5e1a818a386bf2b2d2156465ccff7ed0.html", "raw_html_sha256": "b57ab8113a06a5c45fb7c9d774934db32883c1b3604b159b5f5cf2fc250316c9", "fetched_at": "2026-07-12T02:40:04.898Z", "recordings": [ { "recording_id": "33375f053d2598b5dae3eedab5605762d7ffc855e7c5b56f2940eda90624fbe4", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/46b/46ba0136441fc61b39ae543f3098239d17d58135e1bc1b15405bc8f987949ba8.mp3", "archive_relative_path": "raw/audio/46b/46ba0136441fc61b39ae543f3098239d17d58135e1bc1b15405bc8f987949ba8.mp3" } ] } ], "prediction": "Ta's'g na gisijig ta'n tujiw gisite'g?", "reference": "Ta'sijig igatne'suinug esgmaljig?" }, { "id": "mic-sent-fa44107245180a728d893ea5:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The tongue of a cat has a very rough texture.", "output_text": "Gajue'wj winnu mawgaqe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The tongue of a cat has a very rough texture.", "mic_Latn": "Gajue'wj winnu mawgaqe'g." }, "canonical_ref": "entries/g/gaqe'g/gaqe'g.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-40f4809a323392eb9f54", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gaqe'g/gaqe'g.html", "entry_url": "https://mikmaqonline.org/entries/g/gaqe'g/gaqe'g.html", "headword": "gaqe'g", "example_index": 0, "raw_html_path": "raw/entries/fde3c72d432b561624658f8d3638ea9e23152183b193f442c0f14939182b895a.html", "raw_html_sha256": "a5368f46f95a9f6f314c18cc78e9e50e322c29a48237d60fc426dd492b142c77", "fetched_at": "2026-07-12T02:38:40.282Z", "recordings": [ { "recording_id": "68746307fee083be213c05a86cbc97df2ec76630ef7aabb7e94908d5703aa6d0", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/ae6/ae6ec1ea9c09d709fde1458c24b99854961961718fe1e6115c256ee8f41be161.mp3", "archive_relative_path": "raw/audio/ae6/ae6ec1ea9c09d709fde1458c24b99854961961718fe1e6115c256ee8f41be161.mp3" } ] } ], "prediction": "Gaju'ji'j gaqate'g na gmu'j.", "reference": "Gajue'wj winnu mawgaqe'g." }, { "id": "mic-sent-fa5ad9c96c5add8817f561b1:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The floor at the camp is almost all rotten.", "output_text": "Msaqtaqt wigwomg geget gaqsugulegaq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The floor at the camp is almost all rotten.", "mic_Latn": "Msaqtaqt wigwomg geget gaqsugulegaq." }, "canonical_ref": "entries/s/sugulegaq/sugulegaq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-8f677f3fdf7d76c441c4", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/s/sugulegaq/sugulegaq.html", "entry_url": "https://mikmaqonline.org/entries/s/sugulegaq/sugulegaq.html", "headword": "sugulegaq", "example_index": 0, "raw_html_path": "raw/entries/d181099b329a3535ffe974f5a72f7a8a9244d8517dd137d74c939a4df5c11f8b.html", "raw_html_sha256": "259a8a3f8cba8cc9be4373a7ab004f7416b776e70abdb9b5fce9ac3accb83515", "fetched_at": "2026-07-12T02:45:16.011Z", "recordings": [ { "recording_id": "5d85a384c760660821930661a9a67a3edf343b278c7a2182c9c84adff7fe95db", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/574/574f83bc722f5eeddc091454d6258de1d65b1957ea5e58fb18aadac11d638e98.mp3", "archive_relative_path": "raw/audio/574/574f83bc722f5eeddc091454d6258de1d65b1957ea5e58fb18aadac11d638e98.mp3" } ] } ], "prediction": "Pugwelg'g ta'n tujiw gesatg.", "reference": "Msaqtaqt wigwomg geget gaqsugulegaq." }, { "id": "mic-sent-fb74cf8c9bb753a06f5f15d9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I had a feast of a meal at lunch.", "output_text": "We'gwigweltanaianeg mewlia'gwe'g.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I had a feast of a meal at lunch.", "mic_Latn": "We'gwigweltanaianeg mewlia'gwe'g." }, "canonical_ref": "entries/g/gweltanat/gweltanat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6d337a74298503b76618", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/gweltanat/gweltanat.html", "entry_url": "https://mikmaqonline.org/entries/g/gweltanat/gweltanat.html", "headword": "gweltanat", "example_index": 0, "raw_html_path": "raw/entries/26b7a8975d76110e2130eb2cf2104bee7ddb465f851552d4b9385fa6b5effac8.html", "raw_html_sha256": "34c8588c0a1418ecb2857d7090f2a4f51e1ce99f20f0fbe55b8e932e015417fc", "fetched_at": "2026-07-12T02:40:02.488Z", "recordings": [ { "recording_id": "3e6c8e546240893b55fa7cccb1ac008cc62f85b64ec75a0099cdcf1614ef0a9d", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/646/64621cd2901d93a4acaa0950b2fd43887fcd3253c125222ed52b5883b79072aa.mp3", "archive_relative_path": "raw/audio/646/64621cd2901d93a4acaa0950b2fd43887fcd3253c125222ed52b5883b79072aa.mp3" } ] } ], "prediction": "Pugwelg na wesgowaqan.", "reference": "We'gwigweltanaianeg mewlia'gwe'g." }, { "id": "mic-sent-fbf7c03db908b3c19926fe73:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I would like it if my car was colored black.", "output_text": "Gsatmug maqtawe'g's nutepaqan.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I would like it if my car was colored black.", "mic_Latn": "Gsatmug maqtawe'g's nutepaqan." }, "canonical_ref": "entries/m/maqtawe'g/maqtawe'g.html#example-1", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-13519d10316c989b0a6f", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/maqtawe'g/maqtawe'g.html", "entry_url": "https://mikmaqonline.org/entries/m/maqtawe'g/maqtawe'g.html", "headword": "maqtawe'g", "example_index": 1, "raw_html_path": "raw/entries/a9ce9378d67d1d89cfa14175180980df99bc602bc85eea54e4abd03764a7f470.html", "raw_html_sha256": "abbd035b3f9d01191274de0fb9d7787b22e9ee0fbc0abad3a4decb0d6add3ed3", "fetched_at": "2026-07-12T02:40:51.462Z", "recordings": [ { "recording_id": "69555d5828066ef12824e6b4842cfa6a58edbe2a66a333d4ea84854a6c671a0d", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/46f/46fed5b40fc480192d11afa096c33ee329ae6401ed66766f0e23b5565516fd14.mp3", "archive_relative_path": "raw/audio/46f/46fed5b40fc480192d11afa096c33ee329ae6401ed66766f0e23b5565516fd14.mp3" } ] } ], "prediction": "Pilei nige' negm na utepaqan.", "reference": "Gsatmug maqtawe'g's nutepaqan." }, { "id": "mic-sent-fc5129734616cdbea463cee9:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "It's really stormy today.", "output_text": "We'guimtuuna'q gisgug.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "It's really stormy today.", "mic_Latn": "We'guimtuuna'q gisgug." }, "canonical_ref": "entries/m/metuguna'q/metuguna'q.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-ce8880f0751573ed0fb3", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/m/metuguna'q/metuguna'q.html", "entry_url": "https://mikmaqonline.org/entries/m/metuguna'q/metuguna'q.html", "headword": "metuguna'q", "example_index": 0, "raw_html_path": "raw/entries/66e06f8c6091b0712f0aab5faa1cacba23907ca528e6372f2cf3179591b8ca50.html", "raw_html_sha256": "ee0c5f5768efe54e8e73729926d1b9f93a497dbf38b7529ce8809bce1025e4c2", "fetched_at": "2026-07-12T02:41:29.204Z", "recordings": [ { "recording_id": "d6654d268a3efe38e1d43aec994b24914323e1b8f680847ced9288be32e4c650", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/39a/39a5ddd48508fc91f26bf14871279e41a2b9613287b26e99d7f56ac14b336b37.mp3", "archive_relative_path": "raw/audio/39a/39a5ddd48508fc91f26bf14871279e41a2b9613287b26e99d7f56ac14b336b37.mp3" } ] } ], "prediction": "Gisgug na gisgug.", "reference": "We'guimtuuna'q gisgug." }, { "id": "mic-sent-fc8ed5e2673191672ec80789:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Does the horned serpent really exist?", "output_text": "Gjitmei eig na jipijga'm?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Does the horned serpent really exist?", "mic_Latn": "Gjitmei eig na jipijga'm?" }, "canonical_ref": "entries/j/jipijga'm/jipijga'm.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-becf6c86de6252800832", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/j/jipijga'm/jipijga'm.html", "entry_url": "https://mikmaqonline.org/entries/j/jipijga'm/jipijga'm.html", "headword": "jipijga'm", "example_index": 0, "raw_html_path": "raw/entries/bb3168549cbd0b4f5bf6c7844a6f11ebe368dc40d4c182448f8466ebfeab478d.html", "raw_html_sha256": "1c4e0e94f360445608741c5cd46700df9b3082ef9fedf0b38b525cf579033acd", "fetched_at": "2026-07-12T02:40:26.150Z", "recordings": [ { "recording_id": "17eb797192efcafe76186938e6184571c3a0debde7c22fc4294e109f40e74400", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f19/f190352404a7f59cad172fe3ffbd958ff51bf5d06357e87426490e350dce76df.mp3", "archive_relative_path": "raw/audio/f19/f190352404a7f59cad172fe3ffbd958ff51bf5d06357e87426490e350dce76df.mp3" } ] } ], "prediction": "Gi's gi's na wi'gwi'g?", "reference": "Gjitmei eig na jipijga'm?" }, { "id": "mic-sent-fd16fba3631da817facd9cf0:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "I'm rushing home before they get back.", "output_text": "Enmnqwe'sei gesgmnaq apaita'tigw.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "I'm rushing home before they get back.", "mic_Latn": "Enmnqwe'sei gesgmnaq apaita'tigw." }, "canonical_ref": "entries/e/enmnqwe'set/enmnqwe'set.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-69e61c6215a12d21c2f6", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/enmnqwe'set/enmnqwe'set.html", "entry_url": "https://mikmaqonline.org/entries/e/enmnqwe'set/enmnqwe'set.html", "headword": "enmnqwe'set", "example_index": 0, "raw_html_path": "raw/entries/48505cba46668db59e625ab5197565e68558ee2941112ad475e10ced4302a606.html", "raw_html_sha256": "69bd64deac2b024d73a140c024c13d615b16f12ffc8237fc0c0b0db57de19aa7", "fetched_at": "2026-07-12T02:38:03.594Z", "recordings": [ { "recording_id": "3443463eb36e3dabd9e1111d19506d913fe5eb7a51ad6a9715708f33d67c500c", "speaker_code": "dmm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/56c/56c082e57e0704c36ede33b2eb6a0e2c41bc15a5c4029a69ede96a0ce33c4ae6.mp3", "archive_relative_path": "raw/audio/56c/56c082e57e0704c36ede33b2eb6a0e2c41bc15a5c4029a69ede96a0ce33c4ae6.mp3" } ] } ], "prediction": "Gi's gi's nige' gesgmnaq ma' newte's'g.", "reference": "Enmnqwe'sei gesgmnaq apaita'tigw." }, { "id": "mic-sent-fd44d82f7ae7d6a5a5ef9f9c:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Have you ever seen a bee?", "output_text": "Gi's gi'l nemi't amu?", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Have you ever seen a bee?", "mic_Latn": "Gi's gi'l nemi't amu?" }, "canonical_ref": "entries/a/amu/amu.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a05fb27f10e8b5958830", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/a/amu/amu.html", "entry_url": "https://mikmaqonline.org/entries/a/amu/amu.html", "headword": "amu", "example_index": 0, "raw_html_path": "raw/entries/41f0ca3afa62f148604954d77bcb066d6ac5e34cca36e01d6427521053bba028.html", "raw_html_sha256": "71293c8c59b3735df364e4ca884ec6714f22e2008d84f62c199791412d1bed03", "fetched_at": "2026-07-12T02:36:56.347Z", "recordings": [ { "recording_id": "c8f208411f2bf63cad17cdadd2c4bfadb425fb1bd2f0c93c1505688bb22c72d6", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/cd6/cd620a12a8fe1f4d026443d4f0cac1e9195d589f57c4d662681f1a4961665274.mp3", "archive_relative_path": "raw/audio/cd6/cd620a12a8fe1f4d026443d4f0cac1e9195d589f57c4d662681f1a4961665274.mp3" } ] } ], "prediction": "Gi's gi'l nemi'g nuji'j?", "reference": "Gi's gi'l nemi't amu?" }, { "id": "mic-sent-fd91df9dc96260495e73d24d:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "The bandage is too tight so he/she loosens it.", "output_text": "A'jijgopilaqan wesumseggteg na ewe'ga'toq.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "The bandage is too tight so he/she loosens it.", "mic_Latn": "A'jijgopilaqan wesumseggteg na ewe'ga'toq." }, "canonical_ref": "entries/e/ewe'ga'toq/ewe'ga'toq.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a1586f1024fd35b1e42a", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/e/ewe'ga'toq/ewe'ga'toq.html", "entry_url": "https://mikmaqonline.org/entries/e/ewe'ga'toq/ewe'ga'toq.html", "headword": "ewe'ga'toq", "example_index": 0, "raw_html_path": "raw/entries/fabc7592ce3c4a243feac8e915ce68a1204f86cedbb11d1f86842a0a4b699b11.html", "raw_html_sha256": "4d817e590d462a67536ec3976d49fb54082db05e39b0bff3908caf63f1c91950", "fetched_at": "2026-07-12T02:38:28.325Z", "recordings": [ { "recording_id": "101dadffed5bdc0ce2bc821b3a74aabb27ed10f9fd65dbfdfa0a355dd74ddc50", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/467/46702655bda7e3f1a80a3d0b9238fbe4e1ca60b5855af5e6c2851ff2ec426514.mp3", "archive_relative_path": "raw/audio/467/46702655bda7e3f1a80a3d0b9238fbe4e1ca60b5855af5e6c2851ff2ec426514.mp3" } ] } ], "prediction": "We'gwi'g'p na lugowaqan, gatu gesatg.", "reference": "A'jijgopilaqan wesumseggteg na ewe'ga'toq." }, { "id": "mic-sent-fe89f847ad49dff6d7273cce:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "He/she has been waiting for him/her a long time, yet when he/she saw him/her, he/she didn't speak to him/her.", "output_text": "Gi's sa'q esgipa'tl, toqqatu nemiateg mu gelulagul.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "He/she has been waiting for him/her a long time, yet when he/she saw him/her, he/she didn't speak to him/her.", "mic_Latn": "Gi's sa'q esgipa'tl, toqqatu nemiateg mu gelulagul." }, "canonical_ref": "entries/t/toqqatua/toqqatua.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-a18919728c481bc89d6d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/t/toqqatua/toqqatua.html", "entry_url": "https://mikmaqonline.org/entries/t/toqqatua/toqqatua.html", "headword": "toqqatua", "example_index": 0, "raw_html_path": "raw/entries/1adb8fdfa48d06e64ad831822f936cdbd2b6cc14fbc664b2de08322c1084f7b3.html", "raw_html_sha256": "eaf93b7a8ea1e2679df5f588d9b0311d1486bbbdc6faf3cf86844c648da855df", "fetched_at": "2026-07-12T02:46:04.258Z", "recordings": [ { "recording_id": "07900966e9eed1be1e1b8a7f8ae86c0fccb838428ddefb6401e39b5ad65ced97", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/fbe/fbe6013715a3254bf1856a5847883545934ba7d529dd4e6f29f4297610c4f81d.mp3", "archive_relative_path": "raw/audio/fbe/fbe6013715a3254bf1856a5847883545934ba7d529dd4e6f29f4297610c4f81d.mp3" } ] } ], "prediction": "Gi's gi's gisgug, pas'g ta'n newte's'g, mu gesatg.", "reference": "Gi's sa'q esgipa'tl, toqqatu nemiateg mu gelulagul." }, { "id": "mic-sent-fea5e50cde6875693a6a1797:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "An earthquake really shakes things up.", "output_text": "Giwgw na ma'munpepuetestegeg.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "An earthquake really shakes things up.", "mic_Latn": "Giwgw na ma'munpepuetestegeg." }, "canonical_ref": "entries/g/giwgw/giwgw.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-d15d27701a23c2da263d", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/g/giwgw/giwgw.html", "entry_url": "https://mikmaqonline.org/entries/g/giwgw/giwgw.html", "headword": "giwgw", "example_index": 0, "raw_html_path": "raw/entries/9b5bfa0f89dc7165e57fb86c009f8b415a8e30595d8d4c9bca385b4f64f6fbd0.html", "raw_html_sha256": "6c823f5545b9ce716fd37bd69c5295c367f3875aa9e0e06b7f14da09b60985aa", "fetched_at": "2026-07-12T02:39:45.999Z", "recordings": [ { "recording_id": "8f38f94c7d1f63181b4d10563e3b1a4699ba905032c220fda91ff1a8459a9cd9", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/f05/f05582e713ced0db764a2cbc386e034d0eb311cd03fb775839a6518a96870cea.mp3", "archive_relative_path": "raw/audio/f05/f05582e713ced0db764a2cbc386e034d0eb311cd03fb775839a6518a96870cea.mp3" } ] } ], "prediction": "Pugwelg ta'n tujiw gesatg.", "reference": "Giwgw na ma'munpepuetestegeg." }, { "id": "mic-sent-fefe7901f24f124d504c0ea7:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "\"You have to have a long reach\" he/she tells his/her friend, \"if you want to reach me\".", "output_text": "\"Amujpa pijiptnan\" wipapal telimatl, \"gtu'tepnin\".", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "\"You have to have a long reach\" he/she tells his/her friend, \"if you want to reach me\".", "mic_Latn": "\"Amujpa pijiptnan\" wipapal telimatl, \"gtu'tepnin\"." }, "canonical_ref": "entries/p/pijiptnat/pijiptnat.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-051b632bec7e26c51a65", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/p/pijiptnat/pijiptnat.html", "entry_url": "https://mikmaqonline.org/entries/p/pijiptnat/pijiptnat.html", "headword": "pijiptnat", "example_index": 0, "raw_html_path": "raw/entries/ad502c080e4f85418cf2211f681fa9e97cf52521b73cd4b2520617b69289b0cc.html", "raw_html_sha256": "725d42722f2fc6b7b3fa94112e747c8065cfe790884232226b6518e6bc867c69", "fetched_at": "2026-07-12T02:43:56.545Z", "recordings": [ { "recording_id": "e902ecf5c9d1a75add86de53590e0cbcf775c5f1808c8069932eb0cf88d4570a", "speaker_code": "ewm", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/70e/70e3bf20924dcf1083c89a608b7b7532d295fae0b14857b06a7e28d491e216e7.mp3", "archive_relative_path": "raw/audio/70e/70e3bf20924dcf1083c89a608b7b7532d295fae0b14857b06a7e28d491e216e7.mp3" } ] } ], "prediction": "\"Amujpa we'gwi'g'p\" telte'latl witapal, \"s't ge's goqwei ni'n\".", "reference": "\"Amujpa pijiptnan\" wipapal telimatl, \"gtu'tepnin\"." }, { "id": "mic-sent-ff5d7a91fc0391234dc7e38b:eng-mic", "dataset_id": "migmaq-online-example-parallel-v1.0.0-20260712", "split": "test", "direction": "eng-mic", "tier": "source_attested_dictionary_example", "input_text": "Jean Batiste makes the trail for the Priest.", "output_text": "Sapatis nutawtigmuatl Pa'tlia'sal.", "source_lang": "eng_Latn", "target_lang": "mic_Latn", "translation": { "eng_Latn": "Jean Batiste makes the trail for the Priest.", "mic_Latn": "Sapatis nutawtigmuatl Pa'tlia'sal." }, "canonical_ref": "entries/n/nutawtigmuatl/nutawtigmuatl.html#example-0", "pair_kind": "dictionary_example_sentence", "leakage_group": "micgrp-6cbc8e22f6849535989b", "rights_status": "noncommercial_cc_by_nc_4_0", "approved_for_training": true, "orthography_scope": "source_contemporary_listuguj", "source_records": [ { "entry_id": "entries/n/nutawtigmuatl/nutawtigmuatl.html", "entry_url": "https://mikmaqonline.org/entries/n/nutawtigmuatl/nutawtigmuatl.html", "headword": "nutawtigmuatl", "example_index": 0, "raw_html_path": "raw/entries/015fce0f671a33a8e12825325816c51a5e680c61693c22f4dec389561c914a3d.html", "raw_html_sha256": "56806b6448e5700b37a2cf2c4d78cfcef0c853b366e7762b9f2d3eefab76264a", "fetched_at": "2026-07-12T02:42:56.537Z", "recordings": [ { "recording_id": "2f66eb9da507b5e2d5cb1a5d24ac4e784ea0c583a34a7d912ab4ea257ccf2050", "speaker_code": "jnw", "source_audio_url": "https://mikmaqonline.org/derived/compressed-audio/0af/0af6b5e1b744c36462444b47d3af49fbaba93bf5e73b77fd5fa2ab1f5b8de18e.mp3", "archive_relative_path": "raw/audio/0af/0af6b5e1b744c36462444b47d3af49fbaba93bf5e73b77fd5fa2ab1f5b8de18e.mp3" } ] } ], "prediction": "Je'n Batiste'l etltoqtesgmatl Sa'sinigtug.", "reference": "Sapatis nutawtigmuatl Pa'tlia'sal." } ] }