News for hackers. Stuff that matters.
Re:Voxtral Transcribe 2 by pietz on Wednesday February 04, 2026 @11:47AM (#46888138)
Do we know if this is better than Nvidia Parakeet V3? That has been my go-to model locally and it's hard to imagine there's something even better.
Re:Voxtral Transcribe 2 by tylergetsay on Wednesday February 04, 2026 @12:01PM (#46888332)
I've been using Parakeet V3 locally and totally ancedotaly this feels more accurate but slightly slower
Re:Voxtral Transcribe 2 by czottmann on Wednesday February 04, 2026 @12:54PM (#46889091)
I liked Parakeet v3 a lot until it started to drop whole sentences, willy-nilly.
Re:Voxtral Transcribe 2 by cypherpunks01 on Wednesday February 04, 2026 @05:29PM (#46892790)
Yeah, I think the multilingual improvements in V3 caused some kind of regression for English - I've noticed large blocks occasionally dropped as well, so reverted to v2 for my usage. Specifically nvidia/parakeet-tdt-0.6b-v2 vs nvidia/parakeet-tdt-0.6b-v3
Re:Voxtral Transcribe 2 by WXLCKNO on Wednesday February 04, 2026 @07:56PM (#46894221)
Oh god am I glad to read this. Thought it was my microphone or something.
Re:Voxtral Transcribe 2 by d4rkp4ttern on Wednesday February 04, 2026 @09:46PM (#46895011)
I didn’t see that but I do get a lot of stutters (words or syllables repeated 5+ times), not sure if it’s a model problem or post processing issue in the Handy app.
Re:Voxtral Transcribe 2 by whinvik on Wednesday February 04, 2026 @01:01PM (#46889198)
Came here to ask the same question!
Re:Voxtral Transcribe 2 by m1el on Wednesday February 04, 2026 @01:29PM (#46889613)
Re:Voxtral Transcribe 2 by Multicomp on Wednesday February 04, 2026 @02:19PM (#46890345)
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 it starts work, so very slow batches in terms of feedback latency cycles.

And now you've posted this cool solution which streams audio chunks to a model in infinite small pieces, amazing, just amazing.

Now if only I can figure out how to contribute to Handy or similar to do that Speech To Text in a streaming mode, STT locally will be a solved problem for me.

[1] https://github.com/cjpais/Handy

Re:Voxtral Transcribe 2 by m1el on Wednesday February 04, 2026 @04:32PM (#46892107)
Re:Voxtral Transcribe 2 by kwindla on Wednesday February 04, 2026 @05:00PM (#46892424)
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 by pstroqaty on Thursday February 05, 2026 @02:35AM (#46896820)
Thank you for sharing! Does your implementation allow running the Nemotron model on Vulkan? Like whisper.cpp? I'm curious to try other models, but I don't have Nvidia, so my choices are limited.
Re:Voxtral Transcribe 2 by moffkalast on Wednesday February 04, 2026 @05:34PM (#46892854)
Parakeet is really good imo too, and it's just 0.6B so it can actually run on edge devices. 4B is massive, I don't see Voxtral running realtime on an Orin or fitting on a Hailo. An Orin Nano probably can't even load it at BF16.
Re:Voxtral Transcribe 2 by d4rkp4ttern on Wednesday February 04, 2026 @09:44PM (#46894999)
I’m curious about this too. On my M1 Max MacBook I use the Handy app on macOS with Parakeet V3 and I get near instant transcription, accuracy slightly less than slower Whisper models, but that drop is immaterial when talking to CLI coding agents, which is where I find the most use for this.

https://github.com/cjpais/Handy