Speech-to-text Translation on FLEURS 44 x 11 directions
81S2T Score (X→ara)ESRT-12B
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ESRT-12BSystem Type=End-to-end, Parameters=12B2026.05 | 81 | 83.3 | 84 | 83.2 | 84.9 | 85.7 | 83.5 | 83.8 | 82.4 | 82.1 | 83.9 | 83.4 | |
| ESRT-4BSystem Type=End-to-end, Parameters=4B2026.05 | 78.5 | 80.9 | 81.5 | 80.2 | 82.6 | 83.4 | 81.1 | 81.3 | 80.2 | 79.2 | 81.7 | 81 | |
| MCAT-Large-27BSystem Type=End-to-end, Parameters=27B2026.05 | 78.4 | 80.2 | 80.6 | 79.7 | 82.1 | 83.1 | 80.7 | 81 | 79.8 | 79 | 81.1 | 80.5 | |
| Whisper + NLLB-200-3.3BSystem Type=Cascaded, Parameters=3.3B2026.05 | 75.8 | 71.2 | 80.5 | 75.7 | 80.5 | 76.2 | 77.5 | 78.5 | 74 | 76 | 78.7 | 76.8 | |
| Whisper + LLaMAX3-8B-AlpacaSystem Type=Cascaded, Parameters=8B2026.05 | 73.8 | 77.2 | 81.1 | 75.5 | 79.5 | 79.3 | 77.4 | 70.6 | 75 | 73.5 | 78.7 | 76.5 | |
| SeamlessM4T-V2-LargeSystem Type=End-to-end2026.05 | 71.2 | 65.4 | 83.3 | 67.9 | 76.7 | 71.9 | 71.8 | 75.9 | 70.3 | 70 | 73.8 | 72.6 |