Speech-to-Speech Translation on CVSS-C Fr→En
84.52ASR-BLEUGround Truth
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Ground TruthEvaluation Setting=Reference2026.05 | 84.52 | — | |
| S2ST-Omni 2Evaluation Setting=Single many-to-one model2026.05 | 34.72 | 37.83 | |
| S2ST-OmniEvaluation Setting=Single many-to-one model2026.05 | 33.2 | 35.83 | |
| RosettaSpeechEvaluation Setting=Single many-to-one model2026.05 | 32.16 | 33.11 | |
| HibikiEvaluation Setting=Originally reported2026.05 | 30.5 | — | |
| StreamSpeechEvaluation Setting=Originally reported2026.05 | 28.45 | 32.6 | |
| ComSpeechEvaluation Setting=Originally reported2026.05 | 28.15 | 30.72 | |
| UnitYEvaluation Setting=Originally reported2026.05 | 27.77 | — | |
| SimulS2S-LLMEvaluation Setting=Originally reported2026.05 | 26.93 | — | |
| Translatotron 2Evaluation Setting=Originally reported2026.05 | 26.07 | 28.82 | |
| DASpeechEvaluation Setting=Originally reported2026.05 | 25.03 | — | |
| Whisper–Qwen S2TTEvaluation Setting=Text-level reference2026.05 | — | 35.15 |