Automatic Speech Recognition on Shanghai
10.02CERZipformer
Evaluation Results
| Method | Links | |
|---|---|---|
| ZipformerTraining Data=ASR+ST, Training Steps=320K, Decoding Strategy=Greedy2026.01 | 10.02 | |
| ZipformerTraining Data=ASR-only, Training Steps=312K, Decoding Strategy=Greedy2026.01 | 10.25 | |
| FireRed-AED2026.01 | 58.34 | |
| Paraformer2026.01 | 66.42 |