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

231–240 of 255 posts

Re: Voxtral Transcribe 2

#231

Post by atoav »

whimblepop wrote: post #201
fragmede wrote: post #116

Earlier quoted context omitted.

I had to turn off ad-block to get it to work.

I can see the waveform but it still doesn't work for me. Switched to Edge, disabled all adblocking and privacy extensions, built-in tracking prevention, and "enhanced site security" (whatever that is), and still no dice. I'd love to try it and be impressed, but it seems impossible. :(

Did you check if your mic even works in principle? E.g. using https://www.onlinemictest.com/

If you don't get sound there it won't work anywhere. A surprising number of problems like these can be solved by selecting the correct audio input source (provided your computer shows more than one).

Re: Voxtral Transcribe 2

#232

Post by gingersnap »

idiotsecant wrote: post #136
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

But I actually think that one if the bigger arguments for single language models is the ability to have more languages. Im from Sweden, so I would like to have swedish on extremly high level, but I wouldnt like to have all other small languages on that level beacuse it would inflate the size. So, I actually think having multiple single language models, make it wider and deeper

Re: Voxtral Transcribe 2

#233

Post by viraptor »

chickenimprint wrote: post #147
MarcelOlsz wrote: post #142

Earlier quoted context omitted.

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.

> 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

#234

Post by viraptor »

vkazanov wrote: post #219
gerad wrote: post #175

Earlier quoted context omitted.

As an American, my perspective is that Dutch people speak better English than a large percentage of English people and Americans.

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.

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

#235

Post by viraptor »

DaedalusII wrote: post #168
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…

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

> 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

#237

Post by poulpy123 »

ccleve wrote: post #125

This looks great, but it's not clear to me how to use it for a practical task. I need to transcribe about 10 years worth of monthly meetings. These are government hearings with a variety of speakers. All the videos are on YouTube. What's the most practical and cost-effective way to get reasonably accurate transcripts?

> 10 years worth of monthly meetings

if it's 1 monthly video and thus 120 videos (or so) you could try recall (getrecall.ai not recall.ai that is a similar product with a similar name). They summarize youtube videos, but you get the transcript. AFAIK you cannot batch the processing and you have to add each video one by one, that's why 100 or 200 videos is doable but probably not thousands.

Re: Voxtral Transcribe 2

#238

Post by whimblepop »

atoav wrote: post #231
whimblepop wrote: post #201

Earlier quoted context omitted.

I can see the waveform but it still doesn't work for me. Switched to Edge, disabled all adblocking and privacy extensions, built-in tracking prevention, and "enhanced site security" (whatever that is), and still no dice. I'd love to try it and be impressed, but it seems impossible. :(

Did you check if your mic even works in principle? E.g. using https://www.onlinemictest.com/ If you don't get sound there it won't work anywhere. A surprising number of problems like these can be solved by selecting the correct audio input source (provided your computer shows more than one).

Yep. Mic works fine. My mic even works on the test page! What doesn't work is any of the transcription functionality. :(

Re: Voxtral Transcribe 2

#239

Post by drakenot »

meatmanek wrote: post #215
drakenot wrote: post #185

Earlier quoted context omitted.

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.

Do you mean https://huggingface.co/nvidia/nemotron-speech-streaming-en-0... ?

Yes. That is it

Re: Voxtral Transcribe 2

#240

Post by RestartKernel »

gerad wrote: post #175
timhh wrote: post #153

Earlier quoted context omitted.

You could say the same about Dutch to be fair. 90-95% speak English - I bet that's way higher than in Poland.

As an American, my perspective is that Dutch people speak better English than a large percentage of English people and Americans.

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.
Post reply on HN