voice inference

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Mar 6, 2026 by Sudarshan Kamath · across every show →

Everything said about voice inference, oldest first

Mar 6, 2026 negative
Assertion Not checkable as stated
Kamath: Nvidia GPUs suffer severe memory bottlenecks during voice inference
“And media chips are generally very bad for voice inference. Like if you have 40 gigabytes of RAM in a NVIDIA GPU, you can generally, if you want to do real time, like a hundred milliseconds, you can use maybe two or four gigabytes of it for our models. And bey…”
Sudarshan Kamath Mar 6, 2026 ▶ 59:44 Where SMALL models will Win | Sudarshan kamath, Smallest ai
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.