{"id":"6f6932ad-59f8-4ccb-be9e-5f84598be2f6","slug":"hf-model-openinterx-ugc-videocaptioner-1s1e8oq-t","name":"UGC-VideoCaptioner","description":"Hugging Face model openinterx/UGC-VideoCaptioner. Task: video text to text. Library: transformers. 135 downloads. 4 likes.","capabilities":["transformers","safetensors","qwen2_5_omni","text-to-audio","multimodal","video-captioning","audio-visual","ugc","video-text-to-text","dataset:openinterx/UGC-VideoCap","arxiv:2507.11336","base_model:Qwen/Qwen2.5-Omni-3B","base_model:finetune:Qwen/Qwen2.5-Omni-3B","license:mit","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":38,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:22.680Z"}