Automatic Speech Recognition on Chaoshan
10.6CERZipformer
Evaluation results
| Method | Links | |
|---|---|---|
| ZipformerTraining Data=ASR+ST, Training Steps=320K, Decoding Strategy=Greedy2026.01 | 10.6 | |
| ZipformerTraining Data=ASR-only, Training Steps=312K, Decoding Strategy=Greedy2026.01 | 10.79 | |
| FireRed-AED2026.01 | 78.64 | |
| Paraformer2026.01 | 83.59 |