Add framework introduction, resource links, and model tags

README.md

@@ -3,18 +3,48 @@ base_model: Qwen/Qwen3-Omni-30B-A3B-Instruct
 library_name: peft
 license: apache-2.0
 pipeline_tag: audio-text-to-text
+tags:
+  - qwen3_omni_moe
+  - audio
+  - audio-language-model
+  - audio-text-alignment
+  - rubric-based-evaluation
+  - judge-model
+  - lora
 ---
 
 # FineAudio-Judge
 
-FineAudio-Judge evaluates consistency between audio and text descriptions
-or audio-generation instructions through prompt-derived rubric questions.
-Given an audio sample and a rubric question, it predicts a yes/no answer.
+> A Fine-Grained Evaluation Framework for Complex Text-to-Audio Generation
 
-This repository releases a LoRA adapter obtained by supervised fine-tuning
-the Thinker language model of
+[Code](https://github.com/QwenAudio/FunResearch/tree/main/FineAudio-Judge) |
+[Benchmark](https://huggingface.co/datasets/Zixchen/FineAudio-Judge-Benchmark)
+
+FineAudio-Judge is a fine-grained evaluation framework for assessing
+whether audio matches text descriptions or generation instructions
+for complex audio scenes.
+
+Given an audio–text pair, the framework first structurally decomposes
+the text into events, attributes, and inter-event relations, then
+converts them into atomic binary rubric questions. The audio judge
+answers each question with yes or no based on the audio, assessing
+whether the audio matches the corresponding aspect of the text
+description. The proportion of yes answers forms the overall
+audio–text consistency score.
+
+To train the audio judge, we construct a multi-route corpus covering
+real, composed, and generated audio. Rubric-guided prompt/audio
+perturbations and cross-sample mismatches provide fine-grained
+supervision across varying levels of audio–text consistency.
+
+This repository releases the resulting LoRA adapter, obtained by
+supervised fine-tuning of
 [Qwen3-Omni-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct).
-The adapter must be loaded together with the base model.
+The adapter needs to be loaded together with the base model.
+Rubric decomposition uses a separately configured language-model
+backend in the
+[code repository](https://github.com/QwenAudio/FunResearch/tree/main/FineAudio-Judge),
+while the released adapter performs audio-based rubric judgments.
 
 ## Files