search

m-bain / whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
BSD 2-Clause "Simplified" License
12.52k stars 1.32k forks source link

Adds support for FasterWhisper #121

Open playdasegunda opened 1 year ago

playdasegunda commented 1 year ago

A suggestion would be to add support for Faster Whisper, which is much faster and uses much less VRAM than Whisper. You can use the Whisper Large V2 model and only use 4.6GB VRAM instead of the original 10GB. If you can add this, it will be very useful for the community.

arnavmehta7 commented 1 year ago

Yes, we, or atleast I, need this. 🔮

arnavmehta7 commented 1 year ago

Alright, I researched. Seems like the decoding way, tokenizer of whisper, faster-whisper, and whisperx are quite different.