For usage instructions follow openai/whisper-large-v3-turbo. Note for faster-whisper vocab changes make model.is_multilingual and suppress_tokens 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, ๅฐ่ซๅฅ_, 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)
- Downloads last month
- 957
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support