efwkjn/whisper-ja-anime-v0.3

For usage instructions follow openai/whisper-large-v3-turbo. Note for faster-whisper vocab changes make model.ismultilingual and suppresstokens wrong. Please adjust the code as required if you want to use this with faster-whisper.

Turbo finetune with japanese tokenizer. Full finetune trained 2^19 steps, batch size 64. Smaller vocab with ~1.6x bytes/token allows faster speed with 4 layers vs 2 layer distil (10% larger decoder).

Benchmarks. Short form slightly behind v0.2 (trained less?) but long form much better. Also trained for lyrics but untested.

Acknowledgements

• —Train sets: OOPPEENN, Reazon, 小虫哥_, Common Voice 20, deepghs
• —Test sets: KitsuneX07, TEDxJP, kotoba-tech, Saruwatari-lab, grider-withourai

Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC)