Accented Speech Synthesis on LibriTTS-R (train-clean-100)
73.8US Probability
Kokoro-82M (US Speaker Embedding)
Updated 4mo ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| 73.8 | - | 0.71 | - | 4.38 | 3.42 | 2.83 | ||
| 26.6 | 23.7 | 0.73 | 47 | 3.73 | 7.99 | 5.64 | ||
| 25.97 | - | 0.5 | - | 4.39 | 24.91 | 13.56 | ||
| 16.85 | - | 0.42 | - | 4.38 | 32.66 | 18.32 | ||
| 2.97 | 51.59 | 0.38 | 60 | 3.87 | 13.13 | 7.79 | ||
| 1.89 | 58.86 | 0.28 | 74 | 4.25 | 8.35 | 5.68 | ||
| 0.27 | 86.4 | -0.008 | 75 | 4.16 | 24.15 | 14.78 |