zlacker

[return to "Voxtral Transcribe 2"]
1. simonw+kg[view] [source] 2026-02-04 16:21:17
>>meetpa+(OP)
This demo is really impressive: https://huggingface.co/spaces/mistralai/Voxtral-Mini-Realtim...

Don't be confused if it says "no microphone", the moment you click the record button it will request browser permission and then start working.

I spoke fast and dropped in some jargon and it got it all right - I said this and it transcribed it exactly right, WebAssembly spelling included:

> Can you tell me about RSS and Atom and the role of CSP headers in browser security, especially if you're using WebAssembly?

◧◩
2. tekacs+il[view] [source] 2026-02-04 16:41:58
>>simonw+kg
Having built with and tried every voice model over the last three years, real time and non-real time... this is off the charts compared to anything I've seen before.

And open weight too! So grateful for this.

◧◩◪
3. draken+6Z1[view] [source] 2026-02-05 01:19:24
>>tekacs+il
This past month Parakeet v3 dropped with a streaming ASR model that is 0.6B params, can run on a CPU and is super good.
◧◩◪◨
4. meatma+uo2[view] [source] 2026-02-05 05:16:36
>>draken+6Z1
Do you mean https://huggingface.co/nvidia/nemotron-speech-streaming-en-0... ?
[go to top]