{"id":"4aa858fb-9303-442f-bcb3-96d019bc5b7c","slug":"hf-model-memories-ai-ugc-videocaptioner-10sf5c6-u","name":"UGC-VideoCaptioner","description":"Hugging Face model Memories-ai/UGC-VideoCaptioner. Task: video text to text. Library: transformers. 25 downloads. 3 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":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:08.930Z"}