List your company

Zero-shot Text-to-Speech on Singing Voice

7.66WERVevo2
6.951211.735616.5221.3044Aug 22, 2025

Evaluation results

MethodLinks
Vevo2#Hz=12.5, Data (#hours)=101K, 7K, #Param=872M, PT?=✓2025.087.660.72500
MaskGCT#Hz=50, Data (#hours)=101K, #Param=1048M, PT?=✗2025.0811.710.753-1.74-0.97
Ground Truth2025.0812.650.6581.270.55
Vevo2-base#Hz=12.5, Data (#hours)=101K, 7K, #Param=872M, PT?=✗2025.0815.780.708-0.28-0.09
F5-TTSData (#hours)=101K, #Param=336M, PT?=✗2025.0816.120.597-1.89-1.29
CosyVoice 2#Hz=25, Data (#hours)=167K, #Param=581M, PT?=✓2025.0816.180.659-1.68-1.12
Vevo2-base#Hz=12.5, Data (#hours)=101K, #Param=872M, PT?=✗2025.0819.390.658-1.02-0.48
Vevo2-base#Hz=12.5, Data (#hours)=7K, #Param=872M, PT?=✗2025.0825.380.692-0.69-0.36