how is this related with the main topic?
also it seems your project (by your bio), it would be nice to disclose it as this is self-promotion.
wahnfrieden · 2026-10-28 17:47:56 UTC
How is it for Japanese
mewse-hn · 2026-10-28 20:24:48 UTC
testing it against parakeet right now for ASR, it's slower, heavier, and has a higher error rate. but i'm doing a pass with the embedded translation to see if that's any good, it might be worth it.
e: also i'm testing it with a Q4 quant that might not be full accuracy
mewse-hn · 2026-10-28 20:42:57 UTC
ugh, translation is worse than passing a parakeet transcript to a cloud llm. disappointing model.
solarkraft · 2026-10-28 17:54:30 UTC
> 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.
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?
killingtime74 · 2026-10-28 20:12:27 UTC
There are apps on the Google Play Store where you can run on-device models or connect to OpenRouter where they are run for you. Im using Qwen 3 ASR locally on my android, it's the second most accurate open model after the one in this post.
xpct · 2026-10-28 19:44:56 UTC
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.
jiehong · 2026-10-28 20:28:16 UTC
Agreed. I find Parakeet or Qwen ASR better.
I’m still sad Voxtral 3 wasn’t made open source by Mistral.
vjulian · 2026-10-28 20:27:13 UTC
I have a few thousand audio interviews as MP3, around an hour each and with specialized vocabulary. Typically there are no more than 2 to 3 speakers. Audio quality ranges from mediocre to fair to good.
I was thinking of creating a local app that calls OpenAI’s VTT model. In my most recent evaluation, the OpenAI model was best for my use case. But is that indeed the case?
Comments
e: also i'm testing it with a Q4 quant that might not be full accuracy
Bit unfortunate! Nemotron Streaming in Handy has basically solved dictation for me. It recognizes German mixed with English terms and brand names really well.
Select nemotron in the model selection
Also, there's no mention of Nemotron in that handy. Is that the same Handy GGP was talking about?
I’m still sad Voxtral 3 wasn’t made open source by Mistral.
I was thinking of creating a local app that calls OpenAI’s VTT model. In my most recent evaluation, the OpenAI model was best for my use case. But is that indeed the case?