Speech reconstruction on SEED-TTS zh
1.9WERUniAudio-Token
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| UniAudio-TokenFrame Rate=25Hz, BPS=3252026.05 | 1.9 | 4.25 | |
| StableTokenFrame Rate=25Hz, BPS=3252026.05 | 2.62 | 4.18 | |
| CosyVoice2Frame Rate=25Hz, BPS=3252026.05 | 2.75 | 3.58 | |
| GLM-4-Voice-TokenizerFrame Rate=12.5Hz, BPS=1752026.05 | 3.23 | 4.1 | |
| WavTokenizerFrame Rate=75Hz, BPS=9002026.05 | 4.02 | 3.13 |