search

FL33TW00D / whisper-turbo

Cross-Platform, GPU Accelerated Whisper 🏎️
https://whisper-turbo.com
Apache License 2.0
1.73k stars 76 forks source link

Real time stream from microphone #42

Open FL33TW00D opened 1 year ago

FL33TW00D commented 1 year ago

This takes the project from dumb to magic.

Top tier repo here from which we can learn a lot: https://github.com/wavey-ai/mel-spec

andrew-r-thomas commented 11 months ago

Howdy, I've done some audio programming in the past, this project is super sweet, do you mind if I start to take a crack at this?

FL33TW00D commented 11 months ago

Howdy, I've done some audio programming in the past, this project is super sweet, do you mind if I start to take a crack at this?

It's a ton of work in Rust - if you're up to the challenge reach out to me on Discord: _fleetwood

rdewolff commented 6 months ago

That looks like a killer feature!

FL33TW00D commented 6 months ago

Totally possible! @rdewolff

All future development is being done here: https://github.com/huggingface/ratchet

Should be pretty trivial, someone has already done the hard work: https://github.com/wavey-ai/mel-spec All that needs to be done is plug Ratchet in as a backend to that crate!

I'm developing other models, would be great if someone picked this up. Happy to guide.