Downloads · 30 days
1.2K
5% of all-time downloads
whisper-ja-anime-v0.3
efwkjn/whisper-ja-anime-v0.3
whisper-ja-anime-v0.3 is a automatic speech recognition model from efwkjn. Use it when you need speech turned into text.
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 fa…
All-time downloads
25.4K
Public
Parameters
769M
3.1 GB on disk
Likes
13
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Model type
- whisper
- Access
- Public
- Created
- Jun 1, 2025
- Updated
- Sep 18, 2026
- SHA
- 77edc3f6
Model card
From the Hugging Face model README
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, 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)
- Task
- Automatic Speech Recognition
- Type
- whisper
- Languages
- ja
- Created
- Jun 1, 2025
- Updated
- Sep 18, 2026