USAD models - a MIT-SLS Collection

MIT-SLS 's Collections

USAD models

updated Jun 24

USAD: Universal Speech and Audio Representation via Distillation

USAD: Universal Speech and Audio Representation via Distillation

Paper • 2506.18843 • Published Jun 23 • 12
MIT-SLS/USAD-Small

Feature Extraction • 24.8M • Updated Jul 17 • 131
MIT-SLS/USAD-Base

Feature Extraction • 97.2M • Updated Jul 17 • 710 • 5
MIT-SLS/USAD-Large

Feature Extraction • 0.3B • Updated Jul 17 • 228 • 2