Trending storyDeveloping

NVIDIA releases open multilingual RE-USE speech cleanup model with 9.6M parameters

1 article1 sourcesince Oct 30Last article 1h ago · Oct 30, 4:15 PM ET

Overview

AISummary of 1 article

NVIDIA releases NemotronLabs RE-USE, an open multilingual model that removes background noise, echo and other audio distortions from speech, according to an NVIDIA AI post on X. The model has 9.6M parameters.

NVIDIA says a demo and download are available on Hugging Face at huggingface.co/nvidia/NVIDIA-NemotronLabs-RE-USE.

Written by AI from the articles below · updated Oct 30, 4:25 PM ET

Check the sources:

Latest developmentOct 30, 4:15 PM ET

NVIDIA releases open multilingual RE-USE model for speech cleanup

Article timeline

The articles in this story. Times are ET.

Oct 30

4:15 PM
NVIDIA AI@NVIDIAAIOfficial
NVIDIA releases open multilingual RE-USE model for speech cleanup
AINVIDIA researchers release NemotronLabs RE-USE, an open multilingual model that removes background noise, echo and other audio distortions from speech. The model has 9.6M parameters, and a demo and download are available on Hugging Face.

Heat Trend

Not enough continuous observations to show a trend yet.