{"id":"dec22465-e122-411e-80d6-a67f985c4091","slug":"hf-model-umd-zhou-lab-audiorubrics-119eehz-p","name":"AudioRubrics","description":"Hugging Face model umd-zhou-lab/AudioRubrics. Task: audio text to text. 51 downloads. 3 likes.","capabilities":["safetensors","qwen2_5_omni","audio","audio-reasoning","reinforcement-learning","audio-text-to-text","en","arxiv:2608.02831","base_model:Qwen/Qwen2.5-Omni-7B","base_model:finetune:Qwen/Qwen2.5-Omni-7B","license:other"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:08.617Z"}