Text-to-Speech on CV3-Eval Monolingual (hard-zh)
8.55WER (%)VoxCPM 2
Evaluation Results
| Method | Links | |
|---|---|---|
| VoxCPM 22026.06 | 8.55 | |
| Fish-Audio S22026.06 | 9.1 | |
| dots.ttsTraining Stage=MF, NFE (Number of Function Evaluations)=42026.06 | 9.1 | |
| dots.ttsTraining Stage=SOAR2026.06 | 9.22 | |
| dots.ttsTraining Stage=Pretrain2026.06 | 9.69 | |
| CosyVoice 3Number of Parameters=1.5B2026.06 | 9.77 | |
| CosyVoice 22026.06 | 12.58 |