Open Yaodada12 opened 7 months ago
@Yaodada12 , hello. From my test, large-v3 gave poor quality and no punctuation. But large-v2 gave quite good quality. Then I tried to add option condition_on_previous_text=False
with large-v3 model and I found that the quality has improved a lot. Can you try again with this option ?
My code logic:
model = WhisperModel('large-v3', device='cuda')
segments, info = model.transcribe('zh.m4a', word_timestamps=True, condition_on_previous_text=False)
@Yaodada12 , hello. From my test, large-v3 gave poor quality and no punctuation. But large-v2 gave quite good quality. Then I tried to add option
condition_on_previous_text=False
with large-v3 model and I found that the quality has improved a lot. Can you try again with this option ? My code logic:model = WhisperModel('large-v3', device='cuda') segments, info = model.transcribe('zh.m4a', word_timestamps=True, condition_on_previous_text=False)
Thanks,i will try.
same issue, i use large-v2 for ZH.
@hscspring I cannot even transcribe 'zh'
I use both faster-whisper-v2 and faster-whisper-v3.