It supports Turing T4, but not Ampere…
Any ideas on how to add Ampere support? I have a use case in mind that I would love to try on my 3090 rig
Building voice agents with Nvidia open models
11–20 of 21 posts
Re: Building voice agents with Nvidia open models
#12Voice recognition identifies who you are, speech recognition identifies what you say.
Example:
Voice recognition: arrrrrrgh! (Oh, I know that guy. He always gets irritated when someone uses terms speech and voice recognition wrong)
Speech Recognition: "Why can't you guys keep it straight? It is as simple as knowing the difference between hypothesis and theory."
Re: Building voice agents with Nvidia open models
#13Can't wait for this to land in MacWhisper. I like the idea of the streaming dictation especially when dictating long prompts to Claude Code.
Re: Building voice agents with Nvidia open models
#14It supports Turing T4, but not Ampere…
Any ideas on how to add Ampere support? I have a use case in mind that I would love to try on my 3090 rig
Magpie-TTS needs a kernel compiled targeting Ampere, but it appears to be closed source. It was compiled for the 2018 T4, but not 2020-2024 consumer cards, just 2025 consumer cards.
Re: Building voice agents with Nvidia open models
#15Do any of the top models let you pause and think while speaking? I have to speak non-stop to Gemini assitant and ChatGPT, which is very very useless/unnatural for voice mode. Specially for non-english speakers probably. I sometimes have to think more to translate my thoughts to english.
Re: Building voice agents with Nvidia open models
#16Do any of the top models let you pause and think while speaking? I have to speak non-stop to Gemini assitant and ChatGPT, which is very very useless/unnatural for voice mode. Specially for non-english speakers probably. I sometimes have to think more to translate my thoughts to english.
Have you tried talking to ChatGPT in your native tongue? I was blown away by my mother speaking her native tongue to ChatGPT and having it respond in that language. (It's ever so slightly not a mainstream one.)
Re: Building voice agents with Nvidia open models
#17Do any of the top models let you pause and think while speaking? I have to speak non-stop to Gemini assitant and ChatGPT, which is very very useless/unnatural for voice mode. Specially for non-english speakers probably. I sometimes have to think more to translate my thoughts to english.
Have you tried talking to ChatGPT in your native tongue? I was blown away by my mother speaking her native tongue to ChatGPT and having it respond in that language. (It's ever so slightly not a mainstream one.)
Even in my own language I can't talk without any pauses.
Re: Building voice agents with Nvidia open models
#18Earlier quoted context omitted.
Any ideas on how to add Ampere support? I have a use case in mind that I would love to try on my 3090 rig
Magpie-TTS needs a kernel compiled targeting Ampere, but it appears to be closed source. It was compiled for the 2018 T4, but not 2020-2024 consumer cards, just 2025 consumer cards.
I actually forked the repo, modified the Dockerfile and build/run scripts targeting Ampere and the whole setup is running seamlessly on my 3090, Magpie is running fine and using under 3Gb of memory, ~2Gb for nemotron STT, and ~18Gb for Nemotron Nano 30b. Latencies are great and the turn detection works really well!
I'm going to use this setup as the base for a language learning App for my gf :)
Re: Building voice agents with Nvidia open models
#19Re: Building voice agents with Nvidia open models
#20Earlier quoted context omitted.
Magpie-TTS needs a kernel compiled targeting Ampere, but it appears to be closed source. It was compiled for the 2018 T4, but not 2020-2024 consumer cards, just 2025 consumer cards.
I actually forked the repo, modified the Dockerfile and build/run scripts targeting Ampere and the whole setup is running seamlessly on my 3090, Magpie is running fine and using under 3Gb of memory, ~2Gb for nemotron STT, and ~18Gb for Nemotron Nano 30b. Latencies are great and the turn detection works really well! I'm going to use this setup as the base for a language learning App for my gf :)
I got your fork working (also on a 3090). I was not impressed with the latency or the recommended LLM’s quality.