Modelpublic

Rekin226/whisper-small-moore-v0

sourceHugging Facecc-by-nc-4.0updated 2mo agoView on Hugging Face

0likes9downloads

Model Card

Whisper-small Mooré ASR

openai/whisper-small fine-tuned for Mooré speech→text on ~38k transcribed utterances (anchor language token: yo; always pass language='yo', task='transcribe').

Part of Mooré-Voice — open translation and speech recognition for Mooré (Mòoré / Mossi, ISO 639-3 mos), spoken by ~8 million people in and around Burkina Faso.

Evaluation

Pending — run `scripts/evaluate.py`.

Training data

Community Mooré audio from Hugging Face (see repo data/AUDIO_CORPORA.md): hfdjobii TTS sets + Minervus00 collection. Audio is NOT redistributed — weights only.

Limitations

—Read speech dominates → spontaneous/telephone speech will degrade.
—Speaker diversity is limited.
—WER normalisation strips punctuation/case.

License note

Released CC-BY-NC-4.0 because a large share of the training text derives from sources whose redistribution terms are research-use-only or undeclared (see the repo's data/CORPORA.md / data/AUDIO_CORPORA.md). A fully permissive release is planned once the corpus is rebuilt on cleared sources (Common Voice mos + translatewiki + NLLB-mined).