Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Voxtral Transcribe 2

mistral.ai

Post reply on HN
Print view View original

141–150 of 255 posts

Re: Voxtral Transcribe 2

#141

Post by m1el »

Multicomp wrote: post #106
m1el wrote: post #80

Earlier quoted context omitted.

I've been using nemotron ASR with my own ported inference, and happy about it: https://huggingface.co/nvidia/nemotron-speech-streaming-en-0... https://github.com/m1el/nemotron-asr.cpp https://huggingface.co/m1el/nemotron-speech-streaming-0.6B-g...

I'm so amazed to find out just how close we are to the start trek voice computer. I used to use Dragon Dictation to draft my first novel, had to learn a 'language' to tell the rudimentary engine how to recognize my speech. And then I discovered [1] and have been using it for some basic speech recognition, amazed at what a local model can do. But it can't transcribe any text until I finish recording a file, and then i…

you should check out

https://github.com/pipecat-ai/nemotron-january-2026/

discovered through this twitter post:

https://x.com/kwindla/status/2008601717987045382

Re: Voxtral Transcribe 2

#142

Post by MarcelOlsz »

loire280 wrote: post #135
iagooar wrote: post #81

In English it is pretty good. But talk to it in Polish, and suddenly it thinks you speak Russian? Ukranian? Belarus? I would understand if an American company launched this, but for a company being so proud about their European roots, I think it should have better support for major European languages. I tried English + Polish: > All right, I'm not really sure if transcribing this makes a lot of sense. Maybe not. A ць…

They don't claim to support Polish, but they do support Russian. > The model is natively multilingual, achieving strong transcription performance in 13 languages, including English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch. With a 4B parameter footprint, it runs efficiently on edge devices, ensuring privacy and security for sensitive deployments. I won…

Nobody ever supports Polish. It's the worst. They'll support like, ̵Swahili, but not Polish.

edit: I stand corrected lol. I'll go with "Gaelic" instead.

Re: Voxtral Transcribe 2

#143

Post by ethmarks »

decide1000 wrote: post #59
janalsncm wrote: post #53

I noticed that this model is multilingual and understands 14 languages. For many use cases, we probably only need a single language, and the extra 13 are simply adding extra latency. I believe there will be a trend in the coming years of trimming the fat off of these jack of all trades models. https://aclanthology.org/2025.findings-acl.87/

I think this model proves it's very efficient and accurate.

But it could potentially be even more efficient if it was single-language.

Re: Voxtral Transcribe 2

#144

Post by ethmarks »

raincole wrote: post #121
janalsncm wrote: post #53

I noticed that this model is multilingual and understands 14 languages. For many use cases, we probably only need a single language, and the extra 13 are simply adding extra latency. I believe there will be a trend in the coming years of trimming the fat off of these jack of all trades models. https://aclanthology.org/2025.findings-acl.87/

Imagine if ChatGPT started like this and thought they should trim coding abilities from their language model because most people don't code.

They've already done the inverse and trimmed non-coding abilities from their language model: https://openai.com/index/introducing-gpt-5-2-codex/. There's already precedent for creating domain-specific models.

I think it's nice to have specialized models for specific tasks that don't try to be generalists. Voxtral Transcript 2 is already extremely impressive, so imagine how much better it could be if it specialized in specific languages rather than cramming 14 languages into one model.

That said, generalist models definitely have their uses. I do want multilingual transcribing models to exist, I just also think that monolingual models could potentially achieve even better results for that specific language.

Re: Voxtral Transcribe 2

#145

Post by ethmarks »

keeganpoppen wrote: post #91
janalsncm wrote: post #53

I noticed that this model is multilingual and understands 14 languages. For many use cases, we probably only need a single language, and the extra 13 are simply adding extra latency. I believe there will be a trend in the coming years of trimming the fat off of these jack of all trades models. https://aclanthology.org/2025.findings-acl.87/

uhhh i cast doubt on multi-language support as affecting latency. model size, maybe, but what is the mechanism for making latency worse? i think of model latency as O(log(model size))… but i am open to being wrong / that being a not-good mental model / educated guess.

If encoding more learned languages and grammars and dictionaries makes the model size bigger, it will also increase latency. Try running a 1B model locally and then try to run a 500B model on the same hardware. You'll notice that latency has rather a lot to do with model size.

Re: Voxtral Transcribe 2

#146

Post by londons_explore »

MarcelOlsz wrote: post #142
loire280 wrote: post #135

Earlier quoted context omitted.

They don't claim to support Polish, but they do support Russian. > The model is natively multilingual, achieving strong transcription performance in 13 languages, including English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch. With a 4B parameter footprint, it runs efficiently on edge devices, ensuring privacy and security for sensitive deployments. I won…

Nobody ever supports Polish. It's the worst. They'll support like, ̵Swahili, but not Polish. edit: I stand corrected lol. I'll go with "Gaelic" instead.

200 million people speak Swahili.

39 million people speak Polish, and most of those also speak English or another more common language.

Re: Voxtral Transcribe 2

#147

Post by chickenimprint »

MarcelOlsz wrote: post #142
loire280 wrote: post #135

Earlier quoted context omitted.

They don't claim to support Polish, but they do support Russian. > The model is natively multilingual, achieving strong transcription performance in 13 languages, including English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch. With a 4B parameter footprint, it runs efficiently on edge devices, ensuring privacy and security for sensitive deployments. I won…

Nobody ever supports Polish. It's the worst. They'll support like, ̵Swahili, but not Polish. edit: I stand corrected lol. I'll go with "Gaelic" instead.

Swahili is subcontinental lingua franca spoken by 200M people and growing quickly. Polish is spoken by a shrinking population in one country where English is understood anyways.

Re: Voxtral Transcribe 2

#148

Post by antirez »

fph wrote: post #89

Is there an open source Android keyboard that would support it? Everything I find is based on Whisper, which is from 2022. Ages ago given how fast AI is evolving.

I wish I had a Google Keyboard that could easily run on Whisper Medium. This is already great. But unfortunately would be too much inference cost, incredibly slow. The problem with Whisper is not the inference quality: medium and large are incredible. Is that the base model is not enough, and the only one with fast inference in mobile devices.

Re: Voxtral Transcribe 2

#149

Post by kwindla »

m1el wrote: post #141
Multicomp wrote: post #106

Earlier quoted context omitted.

I'm so amazed to find out just how close we are to the start trek voice computer. I used to use Dragon Dictation to draft my first novel, had to learn a 'language' to tell the rudimentary engine how to recognize my speech. And then I discovered [1] and have been using it for some basic speech recognition, amazed at what a local model can do. But it can't transcribe any text until I finish recording a file, and then i…

you should check out https://github.com/pipecat-ai/nemotron-january-2026/ discovered through this twitter post: https://x.com/kwindla/status/2008601717987045382

Happy to answer questions about this (or work with people on further optimizing the open source inference code here). NVIDIA has more inference tooling coming, but it's also fun to hack on the PyTorch/etc stuff they've released so far.

Re: Voxtral Transcribe 2

#150

Post by colordrops »

simonw wrote: post #20

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 At…

is this demo running fully in the browser?
Post reply on HN