| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Speaker-attributed Automatic Speech Recognition | AISHELL-4 | WER21.36 | 6 | |
| Speaker-attributed Speech Recognition | AISHELL-4 Short-form | DER2.89 | 4 | |
| Multi-speaker speech transcription and diarization | AISHELL-4 5-minute long-form (test) | DER7.73 | 4 | |
| Multi-speaker Transcription | AISHELL-4 Chinese | DER6.77 | 3 |