Automatic Speech Recognition on ASR summary results 12 evaluation dimensions
19.18Health Condition Error RateMOSS-Audio-8B-Instruct
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MOSS-Audio-8B-InstructModel Scale=8B, Instruction Tuning=true2026.06 | 19.18 | 8.76 | 9.81 | 4.31 | 10.18 | 2.7 | 3.2 | 2.75 | 24.04 | 24.36 | 15.26 | 7.69 | 11.3 | |
| Qwen3-Omni-InstructInstruction Tuning=true2026.06 | 20.73 | 15.63 | 16.01 | 4.73 | 11.3 | 2.23 | 2.47 | 1.9 | 17.08 | 18.15 | 11.46 | 5.74 | 11.39 | |
| Kimi-Audio-7B-InstructModel Scale=7B, Instruction Tuning=true2026.06 | 21.11 | 29.34 | 21.76 | 4.68 | 16.38 | 2.2 | 2.15 | 2.66 | 21.02 | 20.61 | 16.74 | 6.12 | 14.12 | |
| MOSS-Audio-4B-InstructModel Scale=4B, Instruction Tuning=true2026.06 | 21.11 | 11.84 | 10.79 | 4.01 | 10.11 | 3.11 | 3.72 | 3.29 | 18.48 | 20.33 | 15.09 | 8.15 | 11.58 | |
| Fun-ASR-NanoModel Scale=Nano2026.06 | 21.99 | 7.8 | 19.35 | 4.76 | 11.23 | 2.98 | 3.46 | 3.78 | 18.38 | 19.82 | 14.95 | 6.08 | 12.04 | |
| Paraformer-LargeModel Scale=Large2026.06 | 22.18 | 43.45 | 32.34 | 4.95 | 12.65 | 3.11 | 4.67 | 5.02 | 17.46 | 20.33 | 14.96 | 7.14 | 15.77 | |
| Qwen2.5-Omni-7BModel Scale=7B2026.06 | 23.85 | 31.91 | 22.69 | 4.56 | 12.97 | 2.52 | 3.16 | 3.64 | 25.38 | 21.01 | 16.13 | 6.78 | 15.05 | |
| SenseVoice-SmallModel Scale=Small2026.06 | 24.04 | 8.89 | 23.79 | 4.92 | 13.9 | 4.13 | 4.93 | 5.57 | 26.66 | 24.06 | 17.63 | 7.55 | 14.5 | |
| GLM-ASR-NanoModel Scale=Nano2026.06 | 24.49 | 22.39 | 51.95 | 4.65 | 11.88 | 3.68 | 5.02 | 4.94 | 27.51 | 28.02 | 17.19 | 7.32 | 17.29 | |
| Qwen2.5-Omni-3BModel Scale=3B2026.06 | 24.65 | 33.87 | 24.24 | 5.54 | 11.66 | 2.76 | 3.56 | 4.32 | 22.15 | 22.91 | 15.17 | 7.24 | 15.26 | |
| Audio-Flamingo-NextVersion=Next2026.06 | 36.13 | 25.85 | 25.8 | 8.25 | 34.53 | 8.64 | 38.85 | 12.84 | 42.9 | 62.13 | 38.3 | 30.18 | 30.19 |