Speech-to-speech translation on CVSS En-Es (test)
19.49ASR-BLEUCMLM + DIFFNORM + CG
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| CMLM + DIFFNORM + CGModel Category=Non-autoregressive, Decoding iterations=15, Classifier-free guidance (w)=0.52024.05 | 19.49 | — | — | |
| CMLM + DIFFNORMModel Category=Non-autoregressive, Decoding iterations=152024.05 | 18.96 | — | — | |
| CMLM + CGModel Category=Non-autoregressive, Decoding iterations=15, Classifier-free guidance (w)=0.52024.05 | 17.06 | 4,651 | 5.34 | |
| ConformerModel Category=Autoregressive2024.05 | 13.75 | 895 | 1.02 | |
| Norm TransformerModel Category=Autoregressive2024.05 | 12.98 | 870 | 1 | |
| CMLM + BiPModel Category=Non-autoregressive, Decoding iterations=152024.05 | 12.62 | — | — | |
| CMLMModel Category=Non-autoregressive, Decoding iterations=152024.05 | 12.58 | 4,651 | 5.34 | |
| TransformerModel Category=Autoregressive2024.05 | 10.07 | 870 | 1 |