Text and Reference Speech Synthesis on First evaluation set EN (Hard)
0.036WERCosyVoice2
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| CosyVoice22026.01 | 0.036 | 3.68 | -0.88 | |
| Ground-truth2026.01 | 0.045 | 4.26 | 0 | |
| FlexiVoice-Base2026.01 | 0.0655 | 3.82 | -0.56 | |
| FlexiVoice2026.01 | 0.0699 | 4.06 | 0.78 | |
| VoxInstruct2026.01 | 0.1261 | 2.66 | -0.86 |