Speech Reconstruction on Seed-TTS English
4.125PESQDashengTokenizer
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DashengTokenizerFramerate=252026.02 | 4.125 | 0.987 | |
| DashengTokenizerFrame Rate=25, RTF=0.00342026.05 | 4.122 | 0.987 | |
| MingTok-AudioFramerate=502026.02 | 4.04 | 0.98 | |
| Ming-UniAudioFrame Rate=50, RTF=0.00502026.05 | 3.976 | 0.983 | |
| UniFlow-AudioFramerate=502026.02 | 3.858 | 0.992 | |
| UniFlow-AudioFrame Rate=50, RTF=0.01672026.05 | 3.833 | 0.992 | |
| DACFrame Rate=50, RTF=0.00432026.05 | 3.786 | 0.969 | |
| DACFramerate=502026.02 | 3.763 | 0.969 | |
| EzAudioFramerate=502026.02 | 3.668 | 0.989 | |
| EzAudioFrame Rate=50, RTF=0.00542026.05 | 3.649 | 0.989 | |
| LoSATokFrame Rate=25, RTF=0.00332026.05 | 3.051 | 0.947 | |
| XCodec 2.0Framerate=502026.02 | 2.37 | 0.93 | |
| XY-TokenizerFrame Rate=12.5, RTF=0.00992026.05 | 2.173 | 0.901 | |
| XY-TokenizerFramerate=12.52026.02 | 2.14 | 0.9 | |
| MimiFramerate=12.52026.02 | 2.01 | 0.89 | |
| SNACRTF=0.00192026.05 | 1.817 | 0.872 | |
| SNACFramerate=-2026.02 | 1.804 | 0.87 |