Text-to-Speech on CV3-Eval Monolingual zh
2.65WERFish-Audio S2
Evaluation Results
| Method | Links | |
|---|---|---|
| Fish-Audio S22026.06 | 2.65 | |
| dots.ttsTraining Stage=Pretrain2026.06 | 3.51 | |
| VoxCPM 22026.06 | 3.65 | |
| dots.ttsTraining Stage=SOAR2026.06 | 3.71 | |
| CosyVoice 3Number of Parameters=1.5B2026.06 | 3.91 | |
| dots.ttsTraining Stage=MF, NFE (Number of Function Evaluations)=42026.06 | 3.95 | |
| CosyVoice 22026.06 | 4.08 |