You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Hi everyone,
I’d like to share audio.cpp support for Nemotron 3.5 ASR 0.6B in native C++/GGML:
https://github.com/0xShug0/audio.cpp
On my RTX 5090, the offline path transcribes a 327.6s audio file in 2.17s:
Some perf numbers on RTX 5090
The goal of audio.cpp is to make local audio models easier to run and integrate without needing a separate Python environment for every model.
Huge thanks to the Nemotron team for releasing the model and making this possible. Feedback, testing, and suggestions are very welcome.
All reactions