Nemotronlabs Re Use

Facts

Noted: AI model that strips noise from audio files and outputs WAV · 2026-11-02
Noted: 9.61 million parameters · 2026-11-02
Noted: multilingual support in mind, removing noise regardless of language · 2026-11-02
Noted: main speaker is prioritized in files where several speakers overlap · 2026-11-02
Noted: ships under the OpenMDW-1.1 license · 2026-11-02
Noted: weights on Hugging Face · 2026-11-02
Noted: browser demo · 2026-11-02
Noted: released as open weights · 2026-11-02

Connections

Produces of: Nvidia

Structured graph also available as JSON at /public/entities/nemotronlabs-re-use. CC BY 4.0.

All coverage

3d ago

NVIDIA Releases NemotronLabs-RE-USE Noise Removal Model as Open Weights

NVIDIA has released NemotronLabs-RE-USE, an AI model that strips noise from audio files and outputs WAV. The model has 9.61 million parameters and is built with multilingual support in mind, removing noise regardless of language. In files where several speakers overlap, the main speaker is prioritized. It ships under the OpenMDW-1.1 license with weights on Hugging Face and a browser demo. GIGAZINE cites posted examples converting in-car recordings mixed with road noise, and audio mixed with speaker echo, into clear audio.