[ICML2026] SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
-
marcoyang/spear-xlarge-speech-audio-v2
Feature Extraction • 0.6B • Updated • 708 • 6 -
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 690 -
marcoyang/spear-base-speech-v2
93.3M • Updated • 82 -
marcoyang/spear-xlarge-speech-audio
Feature Extraction • 0.6B • Updated • 500 • 7
