search

MahmoudAshraf97 / whisper-diarization

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
BSD 2-Clause "Simplified" License
3.28k stars 272 forks source link

Turn off source splitting #32

Closed corneliusgerico closed 1 year ago

corneliusgerico commented 1 year ago

Hi,

What is the simplest way to do this?

Thanks

MahmoudAshraf97 commented 1 year ago

pass --no-stem in the cli arguments

Oheed911 commented 1 year ago

can we do it from the python usage?

MahmoudAshraf97 commented 1 year ago

can we do it from the python usage?

Yes, remove the following code https://github.com/MahmoudAshraf97/whisper-diarization/blob/800d03a0885838ac063b16c5692ff10c81d40d74/diarize.py#L37-L52

and replace it with vocal_target = args.audio or whatever your file name argument is