ArthurFDLR
commented
1 year ago The whisper-youtube Notebook generates transcription files of various types (e.g. txt, srt, json) in your Google Drive. So you can easily load one of these files in another Python script (or any application) for your own custom post-processing.
If you prefer to integrate the source code you mentioned, feel free to branch this repository and modify the Notebook to your needs.
Is it possible to format the text file after getting the transcript from Whisper?
I try to implement the method from https://medium.com/@npolovinkin/how-to-chunk-text-into-paragraphs-using-python-8ae66be38ea6.
and
https://thomasjfrank.com/how-to-transcribe-audio-to-text-with-chatgpt-and-notion/#prepare
not sure how should I combine these code tgt