Show HN: Voxtral Mini 4B Realtime running in the browser

1 points by adefa a day ago · 0 comments · 1 min read

Reader

Hello! Earlier this week Mistral released:

Last time I ported a TTS model to Rust using candle, this time I ported an ASR model to Rust with burn.

I was able to lean on the wgpu backend to get the model running in the browser after sharding it.

Here is the HF Space:

and here are the model weights (q4 + tokenizer):

and the code:

Didn't have a chance to use agent teams with this project, maybe next one! :)

No comments yet.

Settings