USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding
AI & ML interests
Speech and language understanding, Self-supervised learning
Recent Activity
models 10
MIT-SLS/USAD2-XXLarge-Plus
Feature Extraction • 1B • Updated • 9 • 1
MIT-SLS/USAD2-XLarge-Plus
Feature Extraction • 0.7B • Updated • 7 • 1
MIT-SLS/USAD2-Large-Plus
Feature Extraction • 0.3B • Updated • 8 • 1
MIT-SLS/USAD2-XLarge
Feature Extraction • 0.7B • Updated • 11 • 1
MIT-SLS/USAD2-Large
Feature Extraction • 0.3B • Updated • 18 • 1
MIT-SLS/USAD2-Base
Feature Extraction • 97.2M • Updated • 18
MIT-SLS/USAD2-Small
Feature Extraction • 24.8M • Updated • 28
MIT-SLS/USAD-Large
Feature Extraction • 0.3B • Updated • 80 • 2
MIT-SLS/USAD-Base
Feature Extraction • 97.2M • Updated • 166 • 5
MIT-SLS/USAD-Small
Feature Extraction • 24.8M • Updated • 74
datasets 0
None public yet