worstchan/EAT-base_epoch30_pretrain
Feature Extraction
•
90M
•
Updated
•
1.94k
•
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 • 316k • 2 -
worstchan/EAT-large_epoch20_pretrain
Feature Extraction • 0.3B • Updated • 165 -
worstchan/EAT-large_epoch20_finetune_AS2M
Feature Extraction • 0.3B • Updated • 192 • 3 -
EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
Paper • 2401.03497 • Published • 1