Efficiency Evaluation on OpenAudioBench English subsets (test)
2,153.43TPSVocalNet-MDM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=12026.02 | 2,153.43 | 0.0116 | |
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=22026.02 | 1,327.8 | 0.0188 | |
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=42026.02 | 757.58 | 0.0329 | |
| MiMo-Audio2026.02 | 476.51 | 0.4197 | |
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=82026.02 | 390.72 | 0.0639 | |
| VocalNet-8B2026.02 | 374.81 | 0.0667 | |
| Baseline-ARPrediction Type=MTP2026.02 | 374.81 | 0.0667 | |
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=162026.02 | 221.58 | 0.1128 | |
| MiniCPM-o2026.02 | 212.16 | 0.2205 | |
| Baseline-ARPrediction Type=NTP2026.02 | 204.64 | 0.1222 | |
| VITA-Audio2026.02 | 64.62 | 0.1934 | |
| SLAM-Omni2026.02 | 61.13 | 0.818 | |
| Qwen2.5-Omni2026.02 | 58.82 | 0.8484 | |
| GLM-4-Voice2026.02 | 39.06 | 0.32 | |
| Kimi-Audio2026.02 | 30.77 | 0.4062 |