Update README.md

README.md

@@ -5,4 +5,47 @@ base_model:
 - Qwen/Qwen3-Omni-30B-A3B-Instruct
 pipeline_tag: audio-classification
 ---
-A Fine-grained Multi-dimensional Speech understanding model.
+Leveraging the multi-dimensional fine-grained annotations produced by our pipeline, we introduce **FM-Speech**, built upon the frontier Qwen3-Omni (30B MoE) architecture. 
+
+<div align="center">
+  <!-- 请在此处放一张精简的模型输入输出示意图 -->
+  <!--<img width="500px" src="src/model_io.png" alt="Model Input Output Diagram"/> -->
+  <p><i>Input: Raw Speech &emsp; ➔ &emsp; Output: 14-Dimension Fine-Grained Speech Attributes (Structured JSON)</i></p>
+</div>
+
+To overcome modality gaps and text-conditioned hallucinations, FM-Speech is trained using a **Progressive Curriculum Fine-Tuning** framework, decoupling complex auditory comprehension into three incremental stages: Warm-up (MCQ/QA) $\rightarrow$ Capability Ramp-up $\rightarrow$ Final Alignment (Full JSON).
+
+### 🚀 Usage & Environment Setup
+
+Our model is built upon the Qwen3-Omni architecture. We strongly recommend using **vLLM** for the inference and deployment of FM-Speech. 
+
+**Step 1: Create a fresh Python environment** to avoid runtime conflicts and incompatibilities.
+```bash
+conda create -n fmspeech python=3.12
+conda activate fmspeech
+```
+
+**Step 2: Install required packages**
+```bash
+# Install vLLM (Specifically version 0.13.0)
+pip install vllm==0.13.0
+# Note: If you meet an "Undefined symbol" error while using VLLM_USE_PRECOMPILED=1, 
+# please use "pip install -e . -v" to build vLLM from source.
+
+# Install Transformers and Accelerate
+pip install transformers==4.57.3
+pip install accelerate
+
+# Install Qwen Omni utilities and Flash Attention
+pip install qwen-omni-utils -U
+pip install -U flash-attn --no-build-isolation
+```
+
+**Step 3: Run Inference**
+Prepare a sample audio file and run the inference script to generate the 14-dimension JSON output.
+```bash
+python infer.py
+```
+*(See `infer.py` in our repository for detailed loading and inference examples).*
+
+---