worstchan/EAT-base_epoch30_pretrain
Feature Extraction
•
0.1B
•
Updated
•
3.61k
•
1
EAT
Official model series for "EAT: Self-Supervised Pre-Training with Efficient Audio Transformer"
-
-
worstchan/EAT-base_epoch30_finetune_AS2M
Feature Extraction • 0.1B • Updated • 680 -
worstchan/EAT-large_epoch20_pretrain
Feature Extraction • 0.3B • Updated • 46 -
worstchan/EAT-large_epoch20_finetune_AS2M
Feature Extraction • 0.3B • Updated • 232 -
EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
Paper • 2401.03497 • Published • 1