In-context Text-to-Speech on CommonVoice English v13.0 (test)
0.674Sim-oVoicebox
Evaluation results
| Method | Links | ||
|---|---|---|---|
| VoiceboxTraining data=60K hours2023.12 | 0.674 | 7.9 | |
| AUDIOBOX SPEECHTraining data=100K hours2023.12 | 0.607 | 3.7 | |
| YourTTSTraining data=600 hours2023.12 | 0.312 | 10.4 |