Automatic Speech Recognition on Suzhou
10.17CERZipformer
Evaluation Results
| Method | Links | |
|---|---|---|
| ZipformerTraining Data=ASR+ST, Training Steps=320K, Decoding Strategy=Greedy2026.01 | 10.17 | |
| ZipformerTraining Data=ASR-only, Training Steps=312K, Decoding Strategy=Greedy2026.01 | 10.46 | |
| FireRed-AED2026.01 | 77.56 | |
| Paraformer2026.01 | 80.62 |