Voice Cloning on CV3-Eval multilingual voice cloning (test)
2.65WER (zh)Fish Audio S2
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Fish Audio S22026.03 | 2.65 | 2.43 | 3.96 | 2.76 | 2.22 | 2 | 6.26 | 2.04 | 2.78 | 9.1 | 4.4 | |
| CosyVoice3Model Scale=0.5B, Refinement=DiffRO2026.03 | 2.89 | 3.68 | 5.15 | 4.02 | 4.51 | 2.99 | 8.56 | 2.94 | 3.79 | 8.26 | 7.6 | |
| CosyVoice3-0.5B+DiffRO2026.03 | 2.89 | 3.68 | 5.15 | 4.02 | 4.51 | 2.99 | 8.56 | 2.94 | 3.79 | — | — | |
| Fish Audio S12026.03 | 2.98 | 3 | 4.54 | 3.19 | 2.78 | 2.84 | 8.15 | 2.94 | 5.18 | 9.72 | 7.26 | |
| CosyVoice2Refinement=DiffRO2026.03 | 3 | 4.72 | 6.36 | 5.14 | — | — | — | — | — | 10.66 | 10.25 | |
| CosyVoice2+DiffRO2026.03 | 3 | 4.72 | 6.36 | 5.14 | — | — | — | — | — | — | — | |
| CosyVoice3Model Scale=1.5B, Refinement=DiffRO2026.03 | 3.01 | 3.71 | 5.27 | 4.01 | 3.93 | 3.26 | 8.09 | 2.72 | 4.11 | 9.06 | 7.56 | |
| CosyVoice3-1.5B+DiffRO2026.03 | 3.01 | 3.71 | 5.27 | 4.01 | 3.93 | 3.26 | 8.09 | 2.72 | 4.11 | — | — | |
| MOSS-TTS-Local-TransformerMode=Continuation2026.03 | 3.68 | 4.89 | 7.3 | 7.2 | 10.2 | 3.1 | 9.9 | 4.4 | 6.2 | — | — | |
| CosyVoice3-0.5B2026.03 | 3.89 | 5.24 | 10.4 | 12.8 | 7.41 | 4.25 | 12.9 | 6.68 | 6.77 | — | — | |
| CosyVoice3-1.5B2026.03 | 3.91 | 4.99 | 7.57 | 5.69 | 6.43 | 4.47 | 11.8 | 10.5 | 6.64 | — | — | |
| MOSS-TTS-Local-TransformerMode=Clone2026.03 | 3.95 | 4.35 | 10.1 | 5.95 | 4.28 | 3.98 | 10.32 | 5.02 | 5.9 | — | — | |
| CosyVoice22026.03 | 4.08 | 6.32 | 9.13 | 19.7 | — | — | — | — | — | — | — | |
| MOSS-TTSMode=Continuation2026.03 | 4.26 | 5.12 | 7.78 | 7.73 | 10.83 | 3.43 | 10.59 | 4.82 | 6.64 | — | — | |
| MOSS-TTSMode=Clone2026.03 | 4.42 | 4.92 | 10.72 | 6.33 | 4.7 | 4.36 | 11.17 | 5.46 | 6.37 | — | — | |
| Spark-TTS2026.03 | 5.15 | 11 | — | — | — | — | — | — | — | — | — | |
| F5-TTS2026.03 | 5.47 | 8.9 | — | — | — | — | — | — | — | — | — | |
| GPT-SoVits2026.03 | 7.34 | 12.5 | — | — | — | — | — | — | — | — | — |