Hugging Face's logo

Japanese ASR

non-profit
https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0

AI & ML interests

This repo contains models and datasets for Japanese ASR. See our main model https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0.

Organization Card
Community About org cards

Japanese ASR

This repository contains all the models and datasets for train/evaluate the Japanese ASR dataset generated through the process of achieving kotoba-whisper models. Following table shows CER comparison with different data size of ReazonSpeech used to distill openai/whisper-large-v3. The model names follows japanese-asr/distil-whisper-large-v3-ja-reazonspeech-{size of reazonspeech}.

CER

model CommonVoice 8.0 JSUT basic5000 ReazonSpeech Test
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-all 9.20 8.40 11.63
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-large 9.44 8.48 12.60
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-medium 10.89 11.25 16.37
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-small 30.48 38.96 42.29
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-tiny 94.69 95.32 95.82
openai/whisper-large-v3 8.52 7.18 15.18
openai/whisper-large-v2 9.70 8.20 28.50
openai/whisper-large 10.00 8.90 34.40
openai/whisper-base 28.20 25.00 69.40
openai/whisper-medium 11.34 9.87 29.56
openai/whisper-small 15.26 14.22 34.29
openai/whisper-tiny 46.86 35.69 96.69
reazon-research/reazonspeech-nemo-v2 9.07 7.43 11.17

Please find more detailed results at kotoba-whisper codebase.

Collections 6

spaces 1

models 5