Automatic Speech Recognition on Hangzhou
4.95CERZipformer
Evaluation results
| Method | Links | |
|---|---|---|
| ZipformerTraining Data=ASR+ST, Training Steps=320K, Decoding Strategy=Greedy2026.01 | 4.95 | |
| ZipformerTraining Data=ASR-only, Training Steps=312K, Decoding Strategy=Greedy2026.01 | 5.25 | |
| FireRed-AED2026.01 | 37.73 | |
| Paraformer2026.01 | 46.1 |