Downloads · 30 days
20
19% of all-time downloads
whisper-ja-51M
efwkjn/whisper-ja-51M
whisper-ja-51M is a automatic speech recognition model from efwkjn. Use it when you need speech turned into text.
Whisper finetune for Japanese focused on general/anime domains. For usage instructions follow openai/whisper-large-v3-turbo. Due to vocab changes ctranslate2=4.7.1 required for faster-whisper. For inference engines wi…
All-time downloads
105
Public
Parameters
51.4M
103 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors103 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Model type
- whisper
- Access
- Public
- Created
- Jul 26, 2026
- Updated
- Sep 18, 2026
- SHA
- 5b78f64c
Model card
From the Hugging Face model README
Whisper finetune for Japanese focused on general/anime domains. For usage instructions follow openai/whisper-large-v3-turbo. Due to vocab changes ctranslate2>=4.7.1 required for faster-whisper. For inference engines with hardcoded vocab, the token embedding can be padded.
Finetuned from base with pruned vocab and encoder conv adaption, indices can be found in mapping.txt. Trained decoder only for 2^20 steps, batch size 64. Using a 45000 hour corpus (largest source is 17000 of filtered reazonspeech-all) with custom mixing ratio and augmentation to maintain long form performance and timestamps.
Benchmarks. Competitive for size on test sets, particually good on JSUT-book. 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
- Task
- Automatic Speech Recognition
- Type
- whisper
- Languages
- ja
- Created
- Jul 26, 2026
- Updated
- Sep 18, 2026