Nvidia Nemotron 3.5 Transcribe: open ASR for 40 languages

xpct · 2026-10-28T19:44:56.000Z

I played around with Nemotron 3 recently. It's OK, but makes an error every few sentences, at least on the data I worked with (standard vocab). I'm sure we'll get there, but I was pleasantly surprised by how I can recognize words better than it can.

solarkraft · 2026-10-28T17:54:30.000Z

> Transcribe is built for recorded audio, not live streaming.

Bit unfortunate! Nemotron Streaming in Handy has basically solved dictation for me. It recognizes German mixed with English terms and brand names really well.

PorciiVorbesc · 2026-10-28T17:59:11.000Z

Can you share some info how you got that working?

ndom91 · 2026-10-28T18:30:33.000Z

https://handy.computer/

Select nemotron in the model selection

PorciiVorbesc · 2026-10-28T19:04:45.000Z

Oh, since it's called "handy" I expected it would work on mobile phones, as per the name suggests. That seems it only has desktop operating systems.

Also, there's no mention of Nemotron in that handy. Is that the same Handy GGP was talking about?

AkashKaStudio · 2026-10-28T16:57:52.000Z

From the model card, this supports near-field only speaker transcription, experimental but still something not available in any other OSS Speech LLM.

wahnfrieden · 2026-10-28T17:47:56.000Z

How is it for Japanese

mrkn1 · 2026-10-28T17:43:07.000Z

You can use fast transcription on CPU these days, for free and with diarization. Check yapsnap https://github.com/kouhxp/yapsnap