Speech-to-text Translation on FLEURS 11 x 44 directions
83.3ARA -> X ScoreESRT-12B
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ESRT-12BSystem Type=End-to-end, Parameters=12B2026.05 | 83.3 | 83.3 | 88.1 | 83.7 | 85.5 | 83.1 | 85 | 78.5 | 83 | 85.8 | 82.9 | 83.8 | |
| ESRT-4BSystem Type=End-to-end, Parameters=4B2026.05 | 80.1 | 81.3 | 87.2 | 80.8 | 84.4 | 80.9 | 83.3 | 74.2 | 80.6 | 84 | 81.1 | 81.6 | |
| MCAT-Large-27BSystem Type=End-to-end, Parameters=27B2026.05 | 79.7 | 81.3 | 87.1 | 79.9 | 84.2 | 80.8 | 83.4 | 74 | 78.9 | 84.1 | 80.5 | 81.3 | |
| Whisper + NLLB-200-3.3BSystem Type=Cascaded, Parameters=3.3B2026.05 | 78.7 | 80.5 | 84.3 | 79.9 | 82.3 | 80.5 | 81.8 | 71.4 | 78.6 | 83 | 78.9 | 80 | |
| Whisper + LLaMAX3-8B-AlpacaSystem Type=Cascaded, Parameters=8B2026.05 | 76.7 | 79 | 82.2 | 77.9 | 80 | 78.6 | 79.6 | 67.9 | 76.8 | 79.8 | 77.6 | 77.8 | |
| SeamlessM4T-V2-LargeSystem Type=End-to-end2026.05 | 70.1 | 74 | 85.3 | 68.9 | 71.5 | 69.5 | 74.1 | 69.9 | 69 | 72.1 | 72.6 | 72.4 |