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

51–60 of 255 posts

Re: Voxtral Transcribe 2

#51

Post by rafram »

jaggederest wrote: post #43
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 can transcribe Eminem's Rap God fast sequence, really, really impressive.

That's almost certainly in the training data, to be fair.

Re: Voxtral Transcribe 2

#52

Post by rafram »

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…

Not terrible. It missed or mixed up a lot of words when I was speaking quickly (and not enunciating very well), but it does well with normal-paced speech.

Re: Voxtral Transcribe 2

#53

Post by janalsncm »

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/

Re: Voxtral Transcribe 2

#54

Post by XCSme »

Is it me or error rate of 3% is really high?

If you transcribe a minute of conversation, you'll have like 5 words transcribed wrongly. In an hour podcast, that is 300 wrongly transcribed words.

Re: Voxtral Transcribe 2

#55

Post by cootsnuck »

XCSme wrote: post #54

Is it me or error rate of 3% is really high? If you transcribe a minute of conversation, you'll have like 5 words transcribed wrongly. In an hour podcast, that is 300 wrongly transcribed words.

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

Re: Voxtral Transcribe 2

#57

Post by bigyabai »

siddbudd wrote: post #56

Wired advertises this as "Ultra-Fast Translation"[^1]. A bit weird coming from a tech magazine. I hope it's just a "typo". [^1]: https://www.wired.com/story/mistral-voxtral-real-time-ai-tra...

It might be capable of translation; OpenAI Whisper was a transcription model that could do it.

Re: Voxtral Transcribe 2

#58

Post by derefr »

pyprism wrote: post #45
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…

Wow, that’s weird. I tried Bengali, but the text transcribed into Hindi!I know there are some similar words in these languages, but I used pure Bengali that is not similar to Hindi.

Well, on the linked page, it mentions "strong transcription performance in 13 languages, including [...] Hindi" but with no mention of Bengali. It probably doesn't know a lick of Bengali, and is just trying to snap your words into the closest language it does know.

Re: Voxtral Transcribe 2

#59

Post by decide1000 »

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.
Post reply on HN