Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Text-to-Audio Generation on AudioCaption (test)
Loading...
0.526
CLAP Score
Reference
0.41576
0.44438
0.473
0.50162
Jan 30, 2023
CLAP Score
FID
KL Divergence
MOS-Q
MOS-F
Updated 4d ago
Evaluation Results
Method
Method
Links
CLAP Score
FID
KL Divergence
MOS-Q
MOS-F
Reference
2023.01
0.526
-
-
74.7
80.5
Make-An-Audio
Text-cond=T5-Large, Pa...
2023.01
0.486
4.83
2.81
71.8
77.2
Make-An-Audio
Text-cond=CLAP, Params...
2023.01
0.482
4.61
2.79
72.5
78.6
Make-An-Audio
Text-cond=BERT, Params...
2023.01
0.48
5.15
2.89
70.5
77.2
Make-An-Audio
Text-cond=CLIP, Params...
2023.01
0.444
6.45
2.91
72.1
75.4
Diffsound
Text-cond=CLIP, Params...
2023.01
0.42
7.17
3.57
67.1
70.9
Feedback
Search any
task
Search any
task