Speech-to-Speech Translation on CVSS-C De→En
75.53ASR BLEUGround Truth
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Ground TruthEvaluation Setting=Reference2026.05 | 75.53 | — | |
| S2ST-Omni 2Evaluation Setting=Single many-to-one model2026.05 | 33.16 | 35.7 | |
| S2ST-OmniEvaluation Setting=Single many-to-one model2026.05 | 31.25 | 33.34 | |
| RosettaSpeechEvaluation Setting=Single many-to-one model2026.05 | 21.54 | 23.22 | |
| SimulS2S-LLMEvaluation Setting=Originally reported2026.05 | 21.5 | — | |
| StreamSpeechEvaluation Setting=Originally reported2026.05 | 20.93 | 23.36 | |
| UnitYEvaluation Setting=Originally reported2026.05 | 18.74 | — | |
| ComSpeechEvaluation Setting=Originally reported2026.05 | 18.16 | 19.41 | |
| Translatotron 2Evaluation Setting=Originally reported2026.05 | 16.91 | 18.66 | |
| DASpeechEvaluation Setting=Originally reported2026.05 | 16.14 | — | |
| Whisper–Qwen S2TTEvaluation Setting=Text-level reference2026.05 | — | 36.07 |