search

MahmoudAshraf97 / whisper-diarization

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
BSD 2-Clause "Simplified" License
2.44k stars 238 forks source link

Add initial prompt argument support #144

Closed Cognitohazard closed 1 month ago

Cognitohazard commented 6 months ago

Adds "prompt" argument to diarize.py and diarize_parallel.py args parser. Adds passing initial_prompt to batched and non-batched models in transcribe functions.

MahmoudAshraf97 commented 6 months ago

Hello and thanks for the contribution, I've been wanting to add all whisper transcription options to the script but didn't have the capacity to do that, can you extend your PR to do that? it's totally OK if you don't have the time to

Cognitohazard commented 6 months ago

I'll take a look in a few days! The only tricky thing is that whisper and whisperx have different options so I'll have to test a bit to make sure I don't mess anything up.