Voice Conversion on Seed-TTS en (test)
1.96WERGround Truth
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Ground TruthInference mode=Offline, Task setting=Zero-shot2026.04 | 1.96 | — | — | — | |
| Ground TruthZero-shot=true, Streaming=true2026.04 | 1.96 | — | — | — | |
| Seed-VCtiny#Param. (Total)=262M, #Param. (Converter)=27M, Inference mode=Offline, Task setting=Zero-shot2026.04 | 2.24 | 0.41 | 3.67 | 0.069 | |
| Seed-VCsmall#Param. (Total)=296M, #Param. (Converter)=98M, Inference mode=Offline, Task setting=Zero-shot2026.04 | 2.57 | 0.56 | 3.37 | 0.161 | |
| X-VC#Param. (Total)=539M, #Param. (Converter)=44M, Inference mode=Offline, Task setting=Zero-shot2026.04 | 2.83 | 0.63 | 3.31 | 0.014 | |
| X-VC#Param. Total=539M, #Param. Converter=44M, Latency (T_model)=240, Latency (T_compute)=58.17, Zero-shot=true, Streaming=true2026.04 | 3.14 | 0.62 | 3.07 | — | |
| Seed-VCtiny#Param. Total=262M, #Param. Converter=27M, Latency (T_model)=380, Latency (T_compute)=120.75, Zero-shot=true, Streaming=true2026.04 | 3.31 | 0.4 | 2.97 | — |