Automatic Speech Recognition on Shanghai 2
7.36CERZipformer
Evaluation results
| Method | Links | |
|---|---|---|
| ZipformerTraining Data=ASR+ST, Training Steps=320K, Decoding Strategy=Greedy2026.01 | 7.36 | |
| ZipformerTraining Data=ASR-only, Training Steps=312K, Decoding Strategy=Greedy2026.01 | 7.54 | |
| FireRed-AED2026.01 | 56.14 | |
| Paraformer2026.01 | 66.7 |