worstchan/EAT-base_epoch30_pretrain
Feature Extraction • 90M • Updated • 2.12k • 5
EAT
Official model series for "EAT: Self-Supervised Pre-Training with Efficient Audio Transformer"
-
-
worstchan/EAT-base_epoch30_finetune_AS2M
Feature Extraction • 90.4M • Updated • 27.2k • 3 -
worstchan/EAT-large_epoch20_pretrain
Feature Extraction • 0.3B • Updated • 1.09k • 1 -
worstchan/EAT-large_epoch20_finetune_AS2M
Feature Extraction • 0.3B • Updated • 218 • 3 -
EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
Paper • 2401.03497 • Published • 1