USAD models - a MIT-SLS Collection

MIT-SLS 's Collections

USAD models

updated 5 days ago

USAD: Universal Speech and Audio Representation via Distillation

USAD: Universal Speech and Audio Representation via Distillation

Paper • 2506.18843 • Published 5 days ago • 10
MIT-SLS/USAD-Small

Feature Extraction • 0.0B • Updated 5 days ago • 20
MIT-SLS/USAD-Base

Feature Extraction • 0.1B • Updated 5 days ago • 27
MIT-SLS/USAD-Large

Feature Extraction • 0.3B • Updated 5 days ago • 16