Streaming Automatic Speech Recognition on TED-LIUM release-2 (test)
7.8HAT WERConMamba (All-in-One)*
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ConMamba (All-in-One)*Encoder=ConMamba, Strategy=All-in-One, Dual-mode support=Yes, Number of parameters=117.9M2025.12 | 7.8 | 7.6 | 8.9 | |
| ConMamba (All-in-One w/o Dual)Encoder=ConMamba, Strategy=All-in-One, Dual-mode support=No, Number of parameters=235.8M2025.12 | 8.1 | 8.2 | 9.2 | |
| ConMamba (Single)Encoder=ConMamba, Strategy=Single-mode, Number of parameters=574.3M2025.12 | 8.5 | — | 9.3 | |
| Conformer (Single)Encoder=Conformer, Strategy=Single-mode, Number of parameters=576.3M2025.12 | 8.7 | — | 9.1 |