Text and Reference Speech Synthesis on First evaluation set EN Easy
3.71WERCosyVoice2
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| CosyVoice22026.01 | 3.71 | 3.5 | -0.75 | |
| Ground-truth2026.01 | 4.5 | 3.5 | 0 | |
| FlexiVoice2026.01 | 5.23 | 3.62 | 0.89 | |
| FlexiVoice-Base2026.01 | 5.31 | 3.9 | -1.25 | |
| VoxInstruct2026.01 | 14.44 | 2.1 | -1.5 |