News for hackers. Stuff that matters.
Re:Voxtral Transcribe 2 by iagooar on Wednesday February 04, 2026 @01:32PM (#46889692)
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 цьому nie mówisz po polsku. A цьому nie mówisz po polsku, nie po ukrańsku.

Re:Voxtral Transcribe 2 by loire280 on Wednesday February 04, 2026 @04:07PM (#46891785)
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 by MarcelOlsz on Wednesday February 04, 2026 @04:38PM (#46892166)
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 by londons_explore on Wednesday February 04, 2026 @04:56PM (#46892380)
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 by timhh on Wednesday February 04, 2026 @05:10PM (#46892556)
You could say the same about Dutch to be fair. 90-95% speak English - I bet that's way higher than in Poland.
Re:Voxtral Transcribe 2 by gerad on Wednesday February 04, 2026 @06:59PM (#46893709)
As an American, my perspective is that Dutch people speak better English than a large percentage of English people and Americans.
Re:Voxtral Transcribe 2 by vkazanov on Thursday February 05, 2026 @01:19AM (#46896335)
Heh, based on my incorrect and probably wrong experience Dutch and Swedes are the best non-native english speakers in term of both the accent and fluency.
Re:Voxtral Transcribe 2 by viraptor on Thursday February 05, 2026 @04:28AM (#46897646)
Those and Icelandic people. But there's a fun correlation - see how much the US media content is played compared to local one per country. And which countries use subs rather than dubs or voiceovers in cinemas and TV. https://publications.europa.eu/resource/cellar/e4d5cbf4-a839...

If you have exposure to English media from young age and don't get a translation, you learn pretty quickly.

Re:Voxtral Transcribe 2 by RestartKernel on Thursday February 05, 2026 @08:27AM (#46899406)
As a Dutch person, I'm very doubtful that's the case, but I'm willing to bet a good ESL speaker is more aware of common grammatical errors than some native speakers. For example, the your/you're mixup makes no sense if you've had to explicitly learn about English contractions in the first place.
Re:Voxtral Transcribe 2 by chickenimprint on Wednesday February 04, 2026 @04:58PM (#46892406)
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 by viraptor on Thursday February 05, 2026 @04:21AM (#46897597)
> where English is understood anyways.

It's popular. But not that popular - you couldn't assume a random person over 30yo on the street would be able to have a chat.

Re:Voxtral Transcribe 2 by _ache_ on Wednesday February 04, 2026 @07:52PM (#46894185)
Just a side note to remember that this is a mini model. It's very small and yet 12 languages.

I guess a European version can be created but now it's aimed at a world wide distribution.

Re:Voxtral Transcribe 2 by sbinnee on Thursday February 05, 2026 @03:11AM (#46897047)
I guess I will check Korean. OpenAI audio mini is not bad but I always have to make gpt to check and fix transcription.
Re:Voxtral Transcribe 2 by lm28469 on Wednesday February 04, 2026 @02:30PM (#46890478)
> 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.

Try sticking to the supported languages

Re:Voxtral Transcribe 2 by tdb7893 on Wednesday February 04, 2026 @01:37PM (#46889754)
Yeah, it's too bad. Apparently it only performs well in certain languages: "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"
Re:Voxtral Transcribe 2 by ricardonunez on Wednesday February 04, 2026 @02:37PM (#46890566)
It did great English and Spanish, it didn't switch to Portuguese, french nor German, maybe struggle with my accent.
Re:Voxtral Transcribe 2 by scotty79 on Wednesday February 04, 2026 @03:11PM (#46890969)
Try to warn it you are going to switch language to Portugese. Worked for me.
Re:Voxtral Transcribe 2 by yko on Wednesday February 04, 2026 @02:13PM (#46890267)
That's a mix of Polish and Ukrainian in the transcript. Now, if I try speaking Ukrainian, I'm getting transcript in Russian every time. That's upsetting.
Re:Voxtral Transcribe 2 by overfeed on Wednesday February 04, 2026 @03:09PM (#46890949)
Oh no! The model won't translate to an unsupported language, and incorrectly reverts to one that it was explicitly trained on.

The base likely was pretrained on days that included Polish and Ukrainian. You shouldn't be surprised to learn it doesn't perform great on languages it wasn't trained on, or perhaps had the highest share of training data.

Re:Voxtral Transcribe 2 by scotty79 on Wednesday February 04, 2026 @03:12PM (#46890981)
Tell it you are going to speak Polish now. It helps.
Re:Voxtral Transcribe 2 by mystifyingpoi on Wednesday February 04, 2026 @01:36PM (#46889734)
TBH ChatGPT does the same, when I mix Polish and English. Generally getting some cyrillic characters and it gets super confused.
Re:Voxtral Transcribe 2 by moffkalast on Wednesday February 04, 2026 @05:29PM (#46892789)
I'm not sure why but their multilingual performance in general has usually been below average. For a French company, their models are not even close to being best in French, even outdone by the likes of Qwen. I don't think they're focusing on anything but English, the rest is just marketing.
Re:Voxtral Transcribe 2 by DaedalusII on Wednesday February 04, 2026 @06:38PM (#46893518)
polish logically should be rendered in cyrillic as the cyrillic orthography more closely matches the sounds and consonant structure of slavic languages like polish and russian, although this has never been done for church reasons . maybe this is confusing ai
Re:Voxtral Transcribe 2 by iagooar on Wednesday February 04, 2026 @06:46PM (#46893605)
Polish has been written with Latin alphabet since the 13th century. And before it simply wasn't written.

Polish works with the Latin alphabet just fine.

"Do kraju tego, gdzie kruszynę chleba podnoszą z ziemi przez uszanowanie dla darów Nieba.... Tęskno mi, Panie..."

"Mimozami jesień się zaczyna, złotawa, krucha i miła. To ty, to ty jesteś ta dziewczyna, która do mnie na ulicę wychodziła."

Re:Voxtral Transcribe 2 by viraptor on Thursday February 05, 2026 @04:36AM (#46897715)
> although this has never been done for church reasons

That's not the case. Polish uses Latin-like alphabet due to Czech influence and German printers.

Re:Voxtral Transcribe 2 by Cthulhu_ on Thursday February 05, 2026 @03:59AM (#46897432)
Cracking non-English or accented / mispronounced English is the white whale of text-to-speech I think; I don't know about you, but in our day to day chats there's a lot of jargon, randomly inserted English words, etc. And when they speak in English it's often what I call expat-English which is what you get when non-native speakers only speak the language with other non-native speakers.

Add poor microphone quality (using a laptop to broadcast a presentation to a room audience isn't very good) and you get a perfect storm of untranscribeable presentations or meetings.

All I want from e.g. Teams is a good transcript and, more importantly, a clever summary. Because when you think about it, imagine all the words spoken in a meeting and write them down - that's pages and pages of content that nobody would want to read in full.