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

131–140 of 255 posts

Re: Voxtral Transcribe 2

#131

Post by Barbing »

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…

Doesn’t seem to work in Safari on iOS 26.2, iPhone 17 Pro, just about anything extra disabled.

Re: Voxtral Transcribe 2

#132

Post by rhdunn »

XCSme wrote: post #62
cootsnuck wrote: post #55

Earlier quoted context omitted.

The error rate for human transcription can be as high as 5%.

Oh wow, I thought humans are like 0.1% error rate, if they are native speakers and aware of the subject being discussed.

It can depend a lot on different factors like:

- familiarity with the accent and/or speaker;

- speed and style/cadence of the speech;

- any other audio that is happening that can muffle or distort the audio;

- etc.

It can also take multiple passes to get a decent transcription.

Re: Voxtral Transcribe 2

#133

Post by darkwater »

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…

It's really nice although I've got a sentence in French when I was speaking Italian but I corrected myself in the middle of a word.

But I'm definitely going to keep an eye on this for local-only TTS for Home Assistant.

Re: Voxtral Transcribe 2

#134

Post by mr_tox »

antirez wrote: post #17

Italian represents, I believe, the most phonetically advanced human language. It has the right compromise among information density, understandability, and ability to speech much faster to compensate the redundancy. It's like if it had error correction built-in. Note that it's not just that it has the lower error rate, but is also underrepresented in most datasets.

in the end (our) italian language wasn’t optimized by engineers, it was refactored by poets

Re: Voxtral Transcribe 2

#135

Post by loire280 »

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 wonder how much having languages with the same roots (e.g. the romance languages in the list above or multiple Slavic languages) affects the parameter count and the training set. Do you need more training data to differentiate between multiple similar languages? How would swapping, for example, Hindi (fairly distinct from the other 12 supported languages) for Ukrainian and Polish (both share some roots with Russian) affect the parameter count?

Re: Voxtral Transcribe 2

#136

Post by idiotsecant »

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/

The hilarious part of this comment is all the comments around it complaining about not supporting enough languages

Re: Voxtral Transcribe 2

#137

Post by m463 »

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 don't know. What about words inherited from other languages? I think a cross-language model could improve lots of things.

For example, "here it is, voila!" "turn left on el camino real"

Re: Voxtral Transcribe 2

#138

Post by Nimitz14 »

XCSme wrote: post #62
cootsnuck wrote: post #55

Earlier quoted context omitted.

The error rate for human transcription can be as high as 5%.

Oh wow, I thought humans are like 0.1% error rate, if they are native speakers and aware of the subject being discussed.

Most of these errors will not be meaningful. Real speech is full of ambiguities. 3% is low

Re: Voxtral Transcribe 2

#139

Post by mentalgear »

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…

Here European Multilingual-Intelligence truly shines!
Post reply on HN