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.

NVIDIA AIOfficial

@NVIDIAAI

View on X

Sound on 🔊 Listen to the difference.

Our new open multilingual NemotronLabs RE-USE model from NVIDIA researchers cleans up background noise, echo and other audio distortions to make speech clearer. All with just 9.6M parameters.

Try the demo and download the model on @huggingface → https://huggingface.co/nvidia/NVIDIA-NemotronLabs-RE-USE

Open source

Source details

NVIDIA AI · x.comPublished Oct 30, 4:15 PM ET · added here 4:24 PM ET

Original title: Sound on 🔊 Listen to the difference.

Topics

NVIDIA Voice & audio Open-source ecosystem Model releases

NVIDIA releases open multilingual RE-USE model for speech cleanup

Topics

Tags