List your company

Multiple-choice Audio Question Answering on VocalSound (test)

93.92AccuracyQwen2-Audio
92.339292.749693.1693.5704Jun 11, 2024

Evaluation results

MethodLinks
Qwen2-AudioSize=7B, Training Hours=520k2024.0693.92
VideoLLaMA2-AVSize=7B, Training Hours=5k2024.0693.19
Qwen-AudioSize=7B, Training Hours=137k2024.0692.89
VideoLLaMA2.1-AVSize=7B, Training Hours=5k2024.0692.4