Text-to-Speech on CV3-Eval Monolingual (hard-en)
4.37WERdots.tts
Evaluation Results
| Method | Links | |
|---|---|---|
| dots.ttsTraining Stage=MF, NFE (Number of Function Evaluations)=42026.06 | 4.37 | |
| Fish-Audio S22026.06 | 4.4 | |
| dots.ttsTraining Stage=SOAR2026.06 | 4.49 | |
| dots.ttsTraining Stage=Pretrain2026.06 | 5.99 | |
| VoxCPM 22026.06 | 8.48 | |
| CosyVoice 3Number of Parameters=1.5B2026.06 | 10.55 | |
| CosyVoice 22026.06 | 11.96 |