Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-Speech Synthesis on 10-second speech segments
Loading...
1.4
Inference Time (s)
MELLE-R4
1.1632
2.7616
4.36
5.9584
Jul 11, 2024
Inference Time (s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Inference Time (s)
MELLE-R4
AR Steps=156, Reductio...
2024.07
1.4
MELLE-R2
AR Steps=312, Reductio...
2024.07
2.76
VALL-E R
AR Steps=375
2024.07
3.67
CLaM-TTS
2024.07
4.15
MELLE
AR Steps=625
2024.07
5.49
VoiceBox
NFE=64
2024.07
6.4
VALL-E
AR Steps=750
2024.07
7.32
VALL-E 2
AR Steps=750
2024.07
7.32
Feedback
Search any
task
Search any
task