search

collabora / WhisperFusion

WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.
1.45k stars 101 forks source link

VAD in the client / browser? #30

Open djmaze opened 5 months ago

djmaze commented 5 months ago

Doing VAD on the server makes up for a lot of unnecessary traffic and server load. Why not do it on the client?

Thanks to wasm, Silero VAD can be run entirely in the browser. I am building a similar project to this and am using https://github.com/ricky0123/vad. Judging by my tests, it works really well on desktop as well as mobile devices.

zoq commented 5 months ago

The main reason is that we use WhisperLive which implements it on the server side, to enable VAD for every client independent from the implementation. We are happy to merge a client side VAD as well, if someone opens a PR.

kjhenner commented 4 months ago

I'm interested in this. Just gonna post here so I can circle back later and see if there's been progress or I can contribute in some way!

sadimoodi commented 2 months ago

@djmaze i am working on a similar project, can we get in touch? ali@inteslar.com