Automatic Speech Recognition on Mandarin Scenario Aggregate
0.3Hallucination RateOurs
Evaluation results
| Method | Links | |
|---|---|---|
| OursDecoding Mode=offline, Beam Size=3, IA-SFT=true2026.04 | 0.3 | |
| Ours (w/o IA-SFT)Decoding Mode=offline, Beam Size=3, IA-SFT=false2026.04 | 0.5 | |
| Qwen3-Omni-InstDecoding Mode=offline2026.04 | 1.3 | |
| Fun-ASR-nanoDecoding Mode=offline2026.04 | 1.8 | |
| Qwen3-ASR-1.7BDecoding Mode=offline2026.04 | 1.8 | |
| Step-Audio2-miniDecoding Mode=offline2026.04 | 2 | |
| GLM-ASR-nanoDecoding Mode=offline2026.04 | 3 | |
| FireRedASR-LLMDecoding Mode=offline2026.04 | 5.3 |