Closed rphill299 closed 6 months ago
Using PyDub, we should be able to split_on_silence and merge each non-silent segment, then pass this trimmed segment to Whisper. This link has an example
Abandoned because it takes too long compared to just translating the longer audio
Using PyDub, we should be able to split_on_silence and merge each non-silent segment, then pass this trimmed segment to Whisper. This link has an example