Downloads · 30 days
972
2% of all-time downloads
whisper-ja-1.5B
efwkjn/whisper-ja-1.5B
whisper-ja-1.5B 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.
All-time downloads
43.4K
Public
Parameters
1.5B
4.9 GB on disk
Likes
12
Public
Repo makeup
Click a slice to open those files.
.safetensors4.9 GB · 100%
Parameter types
How the weights are stored.
F32907M · 59%
Model card
From the Hugging Face model README
For usage instructions follow openai/whisper-large-v3.
Large-v3 finetune trained as a baseline with smaller checkpoints in progress. Expecting worse long form and equal short form.
Benchmarks. Has occasional repetition issue compared to previous models but achieves competitive/SOTA CER across all tested sets.
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
- Feb 13, 2026
- Updated
- Sep 18, 2026