parent
79b933e66e
commit
6afea795f8
|
|
@ -54,6 +54,7 @@ Thumbs.db
|
|||
# 输入输出
|
||||
output/
|
||||
input/
|
||||
vid_h264/
|
||||
|
||||
# 音频文件（可选，根据需要调整）
|
||||
# *.wav
|
||||
|
|
|
|||
196
INSTALL.md
196
INSTALL.md
|
|
@ -1,196 +0,0 @@
|
|||
# 项目依赖安装指南
|
||||
|
||||
## 📋 环境要求
|
||||
|
||||
- **Python**: 3.10+
|
||||
- **CUDA**: 11.8+ (可选，用于 GPU 加速)
|
||||
- **系统**: Windows 10/11, Linux, macOS
|
||||
|
||||
## 🚀 快速安装
|
||||
|
||||
### 1. 创建虚拟环境
|
||||
|
||||
```bash
|
||||
python -m venv funasr_env
|
||||
```
|
||||
|
||||
### 2. 激活虚拟环境
|
||||
|
||||
**Windows:**
|
||||
```bash
|
||||
funasr_env\Scripts\activate
|
||||
```
|
||||
|
||||
**Linux/macOS:**
|
||||
```bash
|
||||
source funasr_env/bin/activate
|
||||
```
|
||||
|
||||
### 3. 安装 PyTorch (带 CUDA 支持)
|
||||
|
||||
**CUDA 11.8:**
|
||||
```bash
|
||||
pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu118
|
||||
```
|
||||
|
||||
**CPU 版本:**
|
||||
```bash
|
||||
pip install torch torchaudio
|
||||
```
|
||||
|
||||
### 4. 安装 3D-Speaker
|
||||
|
||||
```bash
|
||||
# 克隆 3D-Speaker 项目到父目录
|
||||
cd ..
|
||||
git clone https://github.com/alibaba-damo-academy/3D-Speaker.git
|
||||
|
||||
# 安装 3D-Speaker 依赖
|
||||
cd 3D-Speaker
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
### 5. 安装其他依赖
|
||||
|
||||
```bash
|
||||
# 返回项目目录
|
||||
cd ../audio2
|
||||
|
||||
# 安装 requirements.txt
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
## 📦 依赖说明
|
||||
|
||||
### 核心依赖
|
||||
|
||||
| 包名 | 用途 | 必需 |
|
||||
|------|------|------|
|
||||
| torch | 深度学习框架 | ✅ |
|
||||
| funasr | 语音识别引擎 | ✅ |
|
||||
| modelscope | 模型下载与管理 | ✅ |
|
||||
| speakerlab | 3D-Speaker 说话人分离 | ✅ |
|
||||
| soundfile | 音频文件读写 | ✅ |
|
||||
| librosa | 音频分析 | ✅ |
|
||||
|
||||
### 可选依赖
|
||||
|
||||
| 包名 | 用途 | 何时需要 |
|
||||
|------|------|----------|
|
||||
| onnxruntime-gpu | ONNX 推理加速 | 需要更高性能时 |
|
||||
| Flask | Web API 服务 | 需要部署 Web 服务时 |
|
||||
| SQLAlchemy | 数据库 ORM | 需要持久化存储时 |
|
||||
|
||||
## 🔧 验证安装
|
||||
|
||||
运行测试脚本验证安装：
|
||||
|
||||
```bash
|
||||
# 测试模型加载
|
||||
python test_model_load.py
|
||||
|
||||
# 运行主程序
|
||||
python main.py
|
||||
```
|
||||
|
||||
## ⚠️ 常见问题
|
||||
|
||||
### 1. CUDA 版本不匹配
|
||||
|
||||
**错误信息:**
|
||||
```
|
||||
RuntimeError: CUDA error: no kernel image is available for execution
|
||||
```
|
||||
|
||||
**解决方案:**
|
||||
```bash
|
||||
# 卸载当前 PyTorch
|
||||
pip uninstall torch torchvision torchaudio
|
||||
|
||||
# 根据 CUDA 版本重新安装
|
||||
# CUDA 11.8
|
||||
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
|
||||
|
||||
# CUDA 12.1
|
||||
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
|
||||
```
|
||||
|
||||
### 2. 3D-Speaker 导入失败
|
||||
|
||||
**错误信息:**
|
||||
```
|
||||
ModuleNotFoundError: No module named 'speakerlab'
|
||||
```
|
||||
|
||||
**解决方案:**
|
||||
```bash
|
||||
# 确保 3D-Speaker 在项目父目录
|
||||
# 结构应为:
|
||||
# project/
|
||||
# ├── audio2/
|
||||
# └── 3D-Speaker/
|
||||
|
||||
# 重新安装 3D-Speaker
|
||||
cd 3D-Speaker
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
### 3. 模型下载失败
|
||||
|
||||
**错误信息:**
|
||||
```
|
||||
ConnectionError: Failed to download model from ModelScope
|
||||
```
|
||||
|
||||
**解决方案:**
|
||||
```bash
|
||||
# 使用阿里云镜像
|
||||
export MODELSCOPE_CACHE="./models"
|
||||
|
||||
# 或手动下载模型后放入缓存目录
|
||||
```
|
||||
|
||||
### 4. 内存不足
|
||||
|
||||
**错误信息:**
|
||||
```
|
||||
RuntimeError: CUDA out of memory
|
||||
```
|
||||
|
||||
**解决方案:**
|
||||
- 减少并发数：修改 `main.py` 中的 `max_workers=1`
|
||||
- 使用 CPU 模式：`device='cpu'`
|
||||
- 关闭其他占用 GPU 的程序
|
||||
|
||||
## 📝 依赖版本锁定
|
||||
|
||||
如需精确控制版本，使用：
|
||||
|
||||
```bash
|
||||
# 生成当前环境的依赖快照
|
||||
pip freeze > requirements.lock.txt
|
||||
|
||||
# 使用锁定的版本安装
|
||||
pip install -r requirements.lock.txt
|
||||
```
|
||||
|
||||
## 🎯 最小化安装
|
||||
|
||||
如果只需要基础功能：
|
||||
|
||||
```bash
|
||||
# 最小依赖集
|
||||
pip install torch funasr modelscope soundfile scipy numpy tqdm pyyaml
|
||||
```
|
||||
|
||||
## 📊 磁盘空间需求
|
||||
|
||||
| 组件 | 空间需求 |
|
||||
|------|----------|
|
||||
| 基础依赖 | ~2 GB |
|
||||
| PyTorch (CUDA) | ~3 GB |
|
||||
| FunASR 模型 | ~2 GB |
|
||||
| 3D-Speaker 模型 | ~1 GB |
|
||||
| **总计** | **~8 GB** |
|
||||
|
||||
建议预留 **10 GB** 以上可用空间。
|
||||
82
server.py
82
server.py
|
|
@ -4,6 +4,7 @@ Web API Server for ASR and Speaker Diarization
|
|||
"""
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import gc
|
||||
import json
|
||||
|
|
@ -16,6 +17,8 @@ from werkzeug.utils import secure_filename
|
|||
import uuid
|
||||
from datetime import datetime, timezone
|
||||
|
||||
from lib.convert import convert_to_h264
|
||||
|
||||
|
||||
def make_response(status="success", data=None, errors=None, message=None, extra=None):
|
||||
"""
|
||||
|
|
@ -213,6 +216,78 @@ def result():
|
|||
errors=[str(e)]
|
||||
)), 500
|
||||
|
||||
@app.route('/api/convert', methods=['GET'])
|
||||
def convert():
|
||||
"""视频文件转码"""
|
||||
try:
|
||||
# 从请求参数获取路径
|
||||
path = request.args.get('path', '')
|
||||
|
||||
if not path:
|
||||
return jsonify(make_response(
|
||||
status="error",
|
||||
message="请提供文件路径",
|
||||
errors=["缺少必要参数：path"]
|
||||
)), 400
|
||||
|
||||
# 转码视频文件
|
||||
output_path = convert_to_h264(path)
|
||||
|
||||
return jsonify(make_response(
|
||||
status="success",
|
||||
message="视频文件转码完成",
|
||||
data={"path": output_path}
|
||||
)), 200
|
||||
except Exception as e:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return jsonify(make_response(
|
||||
status="error",
|
||||
message=str(e),
|
||||
errors=[str(e)]
|
||||
)), 500
|
||||
|
||||
@app.route('/api/getVidUrl', methods=['GET'])
|
||||
def getVidUrl():
|
||||
"""获取视频文件URL"""
|
||||
try:
|
||||
# 从请求参数获取路径
|
||||
path = request.args.get('path', '')
|
||||
|
||||
if not path:
|
||||
return jsonify(make_response(
|
||||
status="error",
|
||||
message="请提供文件路径",
|
||||
errors=["缺少必要参数：path"]
|
||||
)), 400
|
||||
|
||||
|
||||
# 检查视频文件是否存在
|
||||
if not Path(f"vid_h264/{Path(path).stem}_h264.mp4").exists():
|
||||
return jsonify(make_response(
|
||||
status="error",
|
||||
message="视频文件不存在",
|
||||
errors=["视频文件不存在"]
|
||||
)), 404
|
||||
|
||||
# 生成视频文件URL
|
||||
url = f"http://localhost:8086/{Path(path).stem}_h264.mp4"
|
||||
print(url)
|
||||
|
||||
return jsonify(make_response(
|
||||
status="success",
|
||||
message="获取成功",
|
||||
data={"url": url}
|
||||
)), 200
|
||||
except Exception as e:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return jsonify(make_response(
|
||||
status="error",
|
||||
message=str(e),
|
||||
errors=[str(e)]
|
||||
)), 500
|
||||
|
||||
if __name__ == '__main__':
|
||||
print("=" * 60)
|
||||
print(" ASR & Speaker Diarization API Server")
|
||||
|
|
@ -220,10 +295,17 @@ if __name__ == '__main__':
|
|||
print("\nAPI 接口:")
|
||||
print(" GET /api/recognize - 文件推理")
|
||||
print(" GET /api/result - 获取文件推理结果")
|
||||
print(" GET /api/convert - 转码视频文件")
|
||||
print(" GET /api/getVidUrl - 获取视频文件URL")
|
||||
print("\n" + "=" * 60)
|
||||
print("启动服务：http://localhost:5000")
|
||||
print("使用 Waitress WSGI 服务器（无超时限制）")
|
||||
print("=" * 60)
|
||||
|
||||
# 启动 Caddy 服务（后台运行）
|
||||
caddy_dir = os.path.join(os.path.dirname(__file__), "vid_h264")
|
||||
caddy_exe = os.path.join(os.path.dirname(__file__), "lib", "caddy_windows_amd64.exe")
|
||||
subprocess.Popen([caddy_exe, "file-server", "--listen", ":8086", "--browse"], cwd=caddy_dir, shell=True)
|
||||
|
||||
from waitress import serve
|
||||
serve(app, host='0.0.0.0', port=5000, threads=4, connection_limit=100)
|
||||
|
|
|
|||
Loading…
Reference in New Issue