Automatic Speech Recognition on Changsha
6.21CERZipformer
Evaluation results
| Method | Links | |
|---|---|---|
| ZipformerTraining Data=ASR+ST, Training Steps=320K, Decoding Strategy=Greedy2026.01 | 6.21 | |
| ZipformerTraining Data=ASR-only, Training Steps=312K, Decoding Strategy=Greedy2026.01 | 7.83 | |
| FireRed-AED2026.01 | 28.71 | |
| Paraformer2026.01 | 33.94 |