List your company

SlideASR on SlideSpeech (dev)

8.62WERVAPO-7B
1.646448.718295.79142.8618Oct 8, 2025

Evaluation results

MethodLinks
VAPO-7BContext usage protocol=Slide image as context (End-to-End)2025.108.629.082.4897.61—
VAPO-3BContext usage protocol=Slide image as context (End-to-End)2025.109.8410.313.6196.54—
Qwen3-Omni-30B-A3BContext usage protocol=Contextless2025.1010.8711.315.0295.04—
MaLa-ASRContext usage protocol=Slide text as context (Pipeline)2025.1011.1411.368.9291.44—
Qwen2.5-Omni-7BContext usage protocol=Contextless2025.1011.7512.25.3994.78—
Qwen2.5-Omni-3BContext usage protocol=Slide image as context (End-to-End)2025.1012.2212.745.2695.17—
Qwen2-AudioContext usage protocol=Contextless2025.1012.5612.858.7291.43—
Qwen2.5-Omni-7BContext usage protocol=Slide image as context (End-to-End)2025.1013.6514.137.1992.84—
Qwen2.5-Omni-3BContext usage protocol=Contextless2025.1015.5316.226.393.76—
MiniCPM-o-2.6Context usage protocol=Contextless2025.1016.0916.688.1491.98—
LCB-netContext usage protocol=Slide text as context (Pipeline)2025.1018.818.1127.972.09—
Qwen3-Omni-30B-A3BContext usage protocol=Slide image as context (End-to-End)2025.1019.8520.649.395.59—
Mi-DashengContext usage protocol=Slide text as context (Pipeline)2025.1033.6735.1813.5693.02—
Qwen3-Omni-30B-A3BContext usage protocol=Slide text as context (Pipeline)2025.1050.4352.8518.0596.45—
Qwen2-AudioContext usage protocol=Slide text as context (Pipeline)2025.10139.81145.0569.9485.4—
MiniCPM-o-2.6Context usage protocol=Slide image as context (End-to-End)2025.10182.96192.8351.0786.26—
Megrez-Omni2025.10————45.14
MiniCPM-o-2.62025.10————57.96
Qwen2.5-Omni-3BParameters=3B2025.10————15.43
Qwen2.5-Omni-7BParameters=7B2025.10————13.71