{"id":"a70394f5-1658-42b9-9029-24eb63b9baf6","slug":"hf-model-audiovisual-caption-asid-captioner-3b-xehn18-11","name":"ASID-Captioner-3B","description":"Hugging Face model AudioVisual-Caption/ASID-Captioner-3B. Task: image text to text. Library: transformers. 102 downloads. 37 likes.","capabilities":["transformers","safetensors","qwen2_5_omni","video-captioning","audiovisual","qwen2.5-omni","instruction-tuning","attribute-structured","quality-verified","image-text-to-text","conversational","en","arxiv:2602.13013","base_model:Qwen/Qwen2.5-Omni-3B","base_model:finetune:Qwen/Qwen2.5-Omni-3B","license:apache-2.0","endpoints_compatible","deploy:azure"],"protocols":[],"safetyScore":80,"overallRank":37,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:33.644Z"}