Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Audio-driven talking face generation on VoxCeleb2
Loading...
8.841
Sc
VASA-1
3.9894
5.24895
6.5085
7.76805
Apr 16, 2024
Sc
Sd
CAPP
ΔP
Updated 4d ago
Evaluation Results
Method
Method
Links
Sc
Sd
CAPP
ΔP
VASA-1
Training data scale=Fu...
2024.04
8.841
6.312
0.468
0.304
VASA-1
Training data scale=10...
2024.04
8.818
6.298
0.457
0.229
Real video
2024.04
7.64
7.189
0.588
0.505
Audio2Head
2024.04
6.172
8.47
0.246
0.26
SadTalker
2024.04
5.843
8.813
0.441
0.275
MakeItTalk
2024.04
4.176
15.513
-0.051
0.21
Feedback
Search any
task
Search any
task