Speech Synthesis on Sound Effect (evaluation)
0.913M-STFTRNDVoC-shared
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RNDVoC-sharedPre-trained=LibriTTS2026.03 | 0.913 | 4.542 | 4.87 | |
| RNDVoC-nonsharedPre-trained=LibriTTS2026.03 | 0.968 | 4.843 | 4.821 | |
| BigVGAN‡Pre-trained=LibriTTS, Training Steps=5M steps2026.03 | 0.998 | 4.837 | 4.851 | |
| WaveFM‡Pre-trained=LibriTTS2026.03 | 1.001 | 4.983 | 4.851 | |
| Vocos‡Pre-trained=LibriTTS2026.03 | 1.11 | 5.715 | 4.745 | |
| BigVGAN-base‡Pre-trained=LibriTTS, Training Steps=5M steps2026.03 | 1.156 | 5.577 | 4.716 | |
| PeriodWave‡Pre-trained=LibriTTS2026.03 | 1.232 | 5.197 | 4.595 | |
| HiFiGAN-V1Pre-trained=LibriTTS2026.03 | 1.462 | 6.971 | 4.291 | |
| AvocodoPre-trained=LibriTTS2026.03 | 1.488 | 6.795 | 4.426 | |
| iSTFTNet-V1Pre-trained=LibriTTS2026.03 | 1.54 | 7.352 | 4.15 | |
| PriorGradPre-trained=LibriTTS2026.03 | 1.61 | 8.106 | 4.289 | |
| FreGradPre-trained=LibriTTS2026.03 | 1.669 | 8.343 | 4.193 | |
| APNet2Pre-trained=LibriTTS2026.03 | 2.138 | 8.318 | 4.303 |