Speech Generation on Speech (test)
5.21PER (%)F5-TTS
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| F5-TTSSize=0.3B, Data=100k+02026.06 | 5.21 | 72.73 | 3.85 | 3.41 | |
| UniVoiceSize=0.3B, Data=30k+35k2026.06 | 5.26 | 67.42 | 3.76 | 3.07 | |
| CosyVoice3Size=0.5B, Data=1000k+02026.06 | 5.3 | 74.94 | 3.75 | 3.19 | |
| Vevo1.5Size=1B, Data=101k+7k2026.06 | 14.1 | 59.07 | 2.85 | 2.77 |