Choose audio sample rate
charles-zablit opened this issue · 1 comments
charles-zablit commented
Description
It seems that whispering expects a sample rate of 16kHz which causes the VAD to fail when another sampling rate is provided.
Would it be possible to send the sample rate in the context and work with that for the rest of the transcription?
Thanks in advance!
shirayu commented
Unfortunately the answer is No, because Whisper also requires sample rate of 16kHz.
https://github.com/openai/whisper/blob/main/whisper/audio.py#L13