File size: 723 Bytes
1482df5 9ec0e4c 28b3c9d 9ec0e4c |
1 2 3 4 5 6 7 8 9 10 |
# clone dataset
git clone https://huggingface.co/datasets/kotoba-tech/kotoba-whisper-eval
# convert to 16khz
ffmpeg -i kotoba-whisper-eval/audio/long_interview_1.mp3 -ar 16000 -ac 1 -c:a pcm_s16le kotoba-whisper-eval/audio/long_interview_1.wav
ffmpeg -i kotoba-whisper-eval/audio/manzai1.mp3 -ar 16000 -ac 1 -c:a pcm_s16le kotoba-whisper-eval/audio/manzai1.wav
ffmpeg -i kotoba-whisper-eval/audio/manzai2.mp3 -ar 16000 -ac 1 -c:a pcm_s16le kotoba-whisper-eval/audio/manzai2.wav
ffmpeg -i kotoba-whisper-eval/audio/manzai3.mp3 -ar 16000 -ac 1 -c:a pcm_s16le kotoba-whisper-eval/audio/manzai3.wav
# run the benchmark
wget https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-faster/raw/main/benchmark.py
python benchmark.py |