Speech Synthesis on AnimeTTS-Bench Zero-Shot Extended (test)
4.38UTMOSCosyVoice 2
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| CosyVoice 2RTF=0.652026.04 | 4.38 | 76 | 72 | 3.9 | |
| ATRIERTF=0.182026.04 | 4.28 | 86 | 84 | 4.1 | |
| VALL-ERTF=0.802026.04 | 4.1 | 71 | 66 | 5.01 | |
| VITSRTF=0.082026.04 | 4.05 | 65 | 62 | 5.21 | |
| FastSpeech 2RTF=0.052026.04 | 3.75 | 60 | 55 | 6.82 |