NVIDIA's NemotronLabs-RE-USE universal speech enhancement model trends on Hugging Face
nvidia · hf · 2026-11-03
NVIDIA released NemotronLabs-RE-USE, a universal speech enhancement model now trending on Hugging Face.
- Audio-to-audio pipeline for universal speech enhancement
- Built on Mamba-SSM architecture, supports multiple input sampling rates
- Language-agnostic, weights in safetensors format
- Open-sourced under openmdw-1.1 license, with two accompanying arXiv papers
More from Multimodal
- Creator: Seedance 2.5's control is so good that AI video is 'essentially solved' — Uncanny_Harry · 2026-11-03
- Watercolor Lord of the Rings image set via Midjourney --sref codes — sergeantsref · 2026-11-03
- 86.2 Agent Hours With Opus 5.5 Produced a Hyperpop Music Video — apples_jimmy · 2026-11-03
- Sume partners with HeyGen: 100 free video generations for first 10,000 users — HeyGen · 2026-11-03
- Open-source ComfyUI node turns instrumental tracks into sung songs with your lyrics — White_Dragon_0 · 2026-11-03
- 'SIX FINGERS': AI girl sings through every era of AI video, 2021 to now — ClaudiaSlop · 2026-11-03