Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Text-to-Audio Generation on AudioSet (eval)
Loading...
24.26
FD
AudioLDM-L-Full
23.2144
30.2722
37.33
44.3878
Jan 29, 2023
FD
IS
KL Divergence
Updated 4d ago
Evaluation Results
Method
Method
Links
FD
IS
KL Divergence
AudioLDM-L-Full
Model Size=L, Training...
2023.01
24.26
7.67
2.07
AudioLDM-L
Model Size=L
2023.01
27.51
7.18
2.49
AudioLDM-S
Model Size=S
2023.01
28.08
6.78
2.51
DiffSound
2023.01
50.4
4.19
3.63
Feedback
Search any
task
Search any
task