search

m-bain / whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
BSD 2-Clause "Simplified" License
10.03k stars 1.05k forks source link

Streaming with whisperx #476

Open evanbrociner opened 9 months ago

evanbrociner commented 9 months ago

Is there a repo or code that allows for real-time streaming with whisperx? Thank you!

Arche151 commented 9 months ago

Whisper itself can't stream, so I dont think so, unfortunately

fgn commented 9 months ago

This issue from whisper.cpp comes to mind Support for realtime audio input . It highlights some issues with doing realtime transcription with whisper in general.

andupotorac commented 7 months ago

Would be great to add support for streaming, because folks have been using Whisper.cpp successfully and implemented streaming - for example gladia.io.

chengxs1994 commented 6 months ago

This submission will allow for segmented streaming using Whisperx, improving client response time, but not for underlying streaming implementations.

Pull request here

SalomonKisters commented 3 months ago

So this can now be used to transcribe live from an audiostream like mic input? If yes, do you maybe know how?

roysG commented 2 months ago

any update?