docs: add offline model download section to README

README.md

@@ -30,6 +30,68 @@ The service follows the same ahserver+longtasks pattern as wan22-service and rea
 
 The model is lazy-loaded on first transcription request and stays in GPU memory for subsequent requests.
 
+## 模型下载（离线部署）
+
+faster-whisper-large-v3-turbo-ct2 是 HuggingFace 模型，需要先下载再部署。
+
+### 方法1: huggingface-cli（推荐）
+
+```bash
+# 安装 huggingface-cli
+pip install huggingface_hub
+
+# 下载模型到指定目录
+huggingface-cli download deepdml/faster-whisper-large-v3-turbo-ct2 \
+  --local-dir /data/ymq/models/deepdml/faster-whisper-large-v3-turbo-ct2 \
+  --local-dir-use-symlinks False
+```
+
+**下载大小**: ~1.6GB  
+**下载时间**: 取决于网络速度（约3-10分钟）
+
+### 方法2: git-lfs
+
+```bash
+# 安装 git-lfs
+git lfs install
+
+# 克隆模型仓库
+cd /data/ymq/models
+mkdir -p deepdml
+cd deepdml
+git clone https://huggingface.co/deepdml/faster-whisper-large-v3-turbo-ct2
+```
+
+### 方法3: wget/curl（单文件）
+
+如果只需要核心文件，可以直接下载：
+
+```bash
+cd /data/ymq/models/deepdml/faster-whisper-large-v3-turbo-ct2
+
+# 下载模型文件
+wget https://huggingface.co/deepdml/faster-whisper-large-v3-turbo-ct2/resolve/main/model.bin
+wget https://huggingface.co/deepdml/faster-whisper-large-v3-turbo-ct2/resolve/main/tokenizer.json
+wget https://huggingface.co/deepdml/faster-whisper-large-v3-turbo-ct2/resolve/main/vocabulary.json
+wget https://huggingface.co/deepdml/faster-whisper-large-v3-turbo-ct2/resolve/main/config.json
+wget https://huggingface.co/deepdml/faster-whisper-large-v3-turbo-ct2/resolve/main/preprocessor_config.json
+```
+
+### 验证下载
+
+```bash
+ls -lh /data/ymq/models/deepdml/faster-whisper-large-v3-turbo-ct2/
+# 应该看到 model.bin (约1.6GB) + tokenizer.json + vocabulary.json + config.json
+```
+
+### 模型来源
+
+- **HuggingFace**: https://huggingface.co/deepdml/faster-whisper-large-v3-turbo-ct2
+- **Base Model**: openai/whisper-large-v3-turbo (CTranslate2 优化版)
+- **License**: MIT
+- **优化**: CTranslate2 格式，比原版 Whisper 快 4 倍，内存占用更少
+
+
 ## Deployment
 
 ### Prerequisites