131 lines
2.3 KiB
Markdown
131 lines
2.3 KiB
Markdown
|
# Qwen2-Audio 语音模型服务
|
|||
|
|
|
|||
|
|
语音交互模型 API 服务，基于 Qwen2-Audio-7B-Instruct。
|
|||
|
|
|
|||
|
|
## 端口
|
|||
|
|
|
|||
|
|
- **服务端口**: 19018
|
|||
|
|
|
|||
|
|
## 功能
|
|||
|
|
|
|||
|
|
- 语音识别 + 对话生成
|
|||
|
|
- 多轮对话支持
|
|||
|
|
- 文本对话接口（可选）
|
|||
|
|
- 对话历史管理
|
|||
|
|
|
|||
|
|
## 部署步骤
|
|||
|
|
|
|||
|
|
### 1. 安装依赖
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
pip install -r requirements.txt
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 2. 启动服务
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
# 方式一：直接启动
|
|||
|
|
python server.py
|
|||
|
|
|
|||
|
|
# 方式二：使用脚本（可指定端口）
|
|||
|
|
PORT=19018 ./start.sh
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 3. 验证服务
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
curl http://localhost:19018/
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
返回：
|
|||
|
|
```json
|
|||
|
|
{"status": "ok", "model": "Qwen/Qwen2-Audio-7B-Instruct", "conversations": 0}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## API 接口
|
|||
|
|
|
|||
|
|
### 语音推理
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
POST /api/voice/inference
|
|||
|
|
Content-Type: multipart/form-data
|
|||
|
|
|
|||
|
|
参数:
|
|||
|
|
- audio: 音频文件 (WAV/MP3/FLAC)
|
|||
|
|
- conversation_id: 对话ID（可选，不传则创建新对话）
|
|||
|
|
- max_length: 最大生成长度（默认256）
|
|||
|
|
|
|||
|
|
返回:
|
|||
|
|
{
|
|||
|
|
"reply": "你好，有什么可以帮助你的吗？",
|
|||
|
|
"conversation_id": "xxx-xxx-xxx",
|
|||
|
|
"timestamp": "2026-04-21T18:00:00"
|
|||
|
|
}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
**示例**：
|
|||
|
|
```bash
|
|||
|
|
curl -X POST http://localhost:19018/api/voice/inference \
|
|||
|
|
-F "audio=@test.wav"
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 文本推理（测试用）
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
POST /api/voice/text
|
|||
|
|
Content-Type: multipart/form-data
|
|||
|
|
|
|||
|
|
参数:
|
|||
|
|
- text: 文本消息
|
|||
|
|
- conversation_id: 对话ID（可选）
|
|||
|
|
|
|||
|
|
返回: 同上
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 获取对话历史
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
GET /api/voice/conversation/{conversation_id}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 删除对话
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
DELETE /api/voice/conversation/{conversation_id}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 多轮对话
|
|||
|
|
|
|||
|
|
第一轮：
|
|||
|
|
```bash
|
|||
|
|
curl -X POST http://localhost:19018/api/voice/inference \
|
|||
|
|
-F "audio=@audio1.wav"
|
|||
|
|
|
|||
|
|
# 返回 conversation_id: "abc-123"
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
第二轮：
|
|||
|
|
```bash
|
|||
|
|
curl -X POST http://localhost:19018/api/voice/inference \
|
|||
|
|
-F "audio=@audio2.wav" \
|
|||
|
|
-F "conversation_id=abc-123"
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 环境变量
|
|||
|
|
|
|||
|
|
| 变量 | 说明 | 默认值 |
|
|||
|
|
|------|------|--------|
|
|||
|
|
| MODEL_NAME | 模型名称 | Qwen/Qwen2-Audio-7B-Instruct |
|
|||
|
|
| MAX_HISTORY_TURNS | 最大历史轮数 | 10 |
|
|||
|
|
|
|||
|
|
## 硬件要求
|
|||
|
|
|
|||
|
|
- **GPU**: 推荐 NVIDIA GPU，显存 ≥ 16GB
|
|||
|
|
- **CPU**: 可运行，但速度较慢
|
|||
|
|
- **内存**: ≥ 32GB
|
|||
|
|
|
|||
|
|
## 注意事项
|
|||
|
|
|
|||
|
|
1. 模型首次加载需要下载约 15GB，请确保网络畅通
|
|||
|
|
2. 音频会自动转换为 16kHz 单声道格式
|
|||
|
|
3. 对话历史存储在内存中，重启服务会丢失
|