Automatic Speech Recognition on AISHELL-2 (WER/CER)
2.16Word Error Rate (WER)Step-Audio-2-mini
Evaluation results
| Method | Links | |
|---|---|---|
| Step-Audio-2-miniVersion=2-mini2026.03 | 2.16 | |
| Qwen3-Omni-A3B-InstructVariant=Omni-A3B-Instruct2026.03 | 2.34 | |
| Kimi-Audio2026.03 | 2.56 | |
| LongCat-Next2026.03 | 2.82 | |
| MiMo-Audio2026.03 | 3.02 | |
| Gemini-3.1-Flash-Lite-previewVersion=3.1, Tier=Flash-Lite-preview2026.03 | 8 | |
| Gemini-2.5-Flash-Lite-previewVersion=2.5, Tier=Flash-Lite-preview2026.03 | 15.33 |