bdim/Canto
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

feat: Enhance README with project description, installation instructions, and acknowledgments

Browse Source
This commit is contained in:
bdim404
2026-02-06 14:13:14 +08:00
parent 2d2c4e9f98
commit 5c0111a7a2
2 changed files with 306 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

168
README.md
View File

@@ -1,6 +1,8 @@
# Qwen3-TTS WebUI # Qwen3-TTS WebUI
A text-to-speech web application based on Qwen3-TTS, supporting custom voice, voice design, and voice cloning. **Unofficial** text-to-speech web application based on Qwen3-TTS, supporting custom voice, voice design, and voice cloning with an intuitive interface.
> This is an unofficial project. For the official Qwen3-TTS repository, please visit [QwenLM/Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS).
[中文文档](./README.zh.md) [中文文档](./README.zh.md)
@@ -48,41 +50,173 @@ A text-to-speech web application based on Qwen3-TTS, supporting custom voice, vo
## Tech Stack ## Tech Stack
Backend: FastAPI + SQLAlchemy + PyTorch + JWT **Backend**: FastAPI + SQLAlchemy + PyTorch + JWT
Frontend: React 19 + TypeScript + Vite + Tailwind + Shadcn/ui - Direct PyTorch inference with Qwen3-TTS models
- Async task processing with batch optimization
- Local model support + Aliyun API integration
## Quick Start **Frontend**: React 19 + TypeScript + Vite + Tailwind + Shadcn/ui
### Backend ## Installation
### Prerequisites
- Python 3.9+ with CUDA support (for local model inference)
- Node.js 18+ (for frontend)
- Git
### 1. Clone Repository
```bash
git clone https://github.com/yourusername/Qwen3-TTS-webUI.git
cd Qwen3-TTS-webUI
```
### 2. Download Models
**Important**: Models are **NOT** automatically downloaded. You need to manually download them first.
For more details, visit the official repository: [Qwen3-TTS Models](https://github.com/QwenLM/Qwen3-TTS)
Navigate to the backend directory:
```bash
cd qwen3-tts-backend
mkdir -p Qwen && cd Qwen
```
**Option 1: Download through ModelScope (Recommended for users in Mainland China)**
```bash
pip install -U modelscope
modelscope download --model Qwen/Qwen3-TTS-Tokenizer-12Hz --local_dir ./Qwen3-TTS-Tokenizer-12Hz
modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --local_dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice
modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --local_dir ./Qwen3-TTS-12Hz-1.7B-VoiceDesign
modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-Base --local_dir ./Qwen3-TTS-12Hz-1.7B-Base
```
Optional 0.6B models (smaller, faster):
```bash
modelscope download --model Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice --local_dir ./Qwen3-TTS-12Hz-0.6B-CustomVoice
modelscope download --model Qwen/Qwen3-TTS-12Hz-0.6B-Base --local_dir ./Qwen3-TTS-12Hz-0.6B-Base
```
**Option 2: Download through Hugging Face**
```bash
pip install -U "huggingface_hub[cli]"
huggingface-cli download Qwen/Qwen3-TTS-Tokenizer-12Hz --local-dir ./Qwen3-TTS-Tokenizer-12Hz
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --local-dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --local-dir ./Qwen3-TTS-12Hz-1.7B-VoiceDesign
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-Base --local-dir ./Qwen3-TTS-12Hz-1.7B-Base
```
Optional 0.6B models (smaller, faster):
```bash
huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice --local-dir ./Qwen3-TTS-12Hz-0.6B-CustomVoice
huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-Base --local-dir ./Qwen3-TTS-12Hz-0.6B-Base
```
**Final directory structure:**
```
Qwen3-TTS-webUI/
├── qwen3-tts-backend/
│ └── Qwen/
│ ├── Qwen3-TTS-Tokenizer-12Hz/
│ ├── Qwen3-TTS-12Hz-1.7B-CustomVoice/
│ ├── Qwen3-TTS-12Hz-1.7B-VoiceDesign/
│ └── Qwen3-TTS-12Hz-1.7B-Base/
```
### 3. Backend Setup
```bash ```bash
cd qwen3-tts-backend cd qwen3-tts-backend
# Create virtual environment
python -m venv venv python -m venv venv
source venv/bin/activate source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt pip install -r requirements.txt
# Install Qwen3-TTS
pip install qwen-tts
# Create configuration file
cp .env.example .env cp .env.example .env
# Edit .env to configure MODEL_BASE_PATH and DEFAULT_BACKEND
# For local model: Ensure MODEL_BASE_PATH points to Qwen model directory # Edit .env file
# For Aliyun: Set DEFAULT_BACKEND=aliyun and configure API key in web settings # For local model: Set MODEL_BASE_PATH=./Qwen
uvicorn main:app --host 0.0.0.0 --port 8000 --reload # For Aliyun API only: Set DEFAULT_BACKEND=aliyun
nano .env # or use your preferred editor
``` ```
### Frontend **Important Backend Configuration** (`.env`):
```env
MODEL_DEVICE=cuda:0 # Use GPU (or cpu for CPU-only)
MODEL_BASE_PATH=./Qwen # Path to your downloaded models
DEFAULT_BACKEND=local # Use 'local' for local models, 'aliyun' for API
DATABASE_URL=sqlite:///./qwen_tts.db
SECRET_KEY=your-secret-key-here # Change this!
```
Start the backend server:
```bash
# Using uvicorn directly
uvicorn main:app --host 0.0.0.0 --port 8000 --reload
# Or using conda (if you prefer)
conda run -n qwen3-tts uvicorn main:app --host 0.0.0.0 --port 8000 --reload
```
Verify backend is running:
```bash
curl http://127.0.0.1:8000/health
```
### 4. Frontend Setup
```bash ```bash
cd qwen3-tts-frontend cd qwen3-tts-frontend
# Install dependencies
npm install npm install
# Create configuration file
cp .env.example .env cp .env.example .env
# Edit .env to configure VITE_API_URL
# Edit .env to set backend URL
echo "VITE_API_URL=http://localhost:8000" > .env
# Start development server
npm run dev npm run dev
``` ```
Visit `http://localhost:5173` ### 5. Access the Application
**First Time Setup**: On first run, a default superuser account will be automatically created: Open your browser and visit: `http://localhost:5173`
**Default Credentials**:
- Username: `admin` - Username: `admin`
- Password: `admin123456` - Password: `admin123456`
- **IMPORTANT**: Please change the password immediately after first login for security! - **IMPORTANT**: Change the password immediately after first login!
### Production Build
For production deployment:
```bash
# Backend: Use gunicorn or similar WSGI server
cd qwen3-tts-backend
gunicorn main:app -w 4 -k uvicorn.workers.UvicornWorker -b 0.0.0.0:8000
# Frontend: Build static files
cd qwen3-tts-frontend
npm run build
# Serve the 'dist' folder with nginx or another web server
```
## Configuration ## Configuration
@@ -164,6 +298,10 @@ All TTS endpoints support an optional `backend` parameter to specify the TTS bac
- `backend: "aliyun"` - Use Aliyun TTS API - `backend: "aliyun"` - Use Aliyun TTS API
- If not specified, uses the user's default backend setting - If not specified, uses the user's default backend setting
## Acknowledgments
This project is built upon the excellent work of the official [Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS) repository by the Qwen Team at Alibaba Cloud. Special thanks to the Qwen Team for open-sourcing such a powerful text-to-speech model.
## License ## License
Apache-2.0 license Apache-2.0 license

168
README.zh.md
View File

@@ -1,6 +1,8 @@
# Qwen3-TTS WebUI # Qwen3-TTS WebUI
基于 Qwen3-TTS 的文本转语音 Web 应用，支持自定义语音、语音设计和语音克隆。 **非官方** 基于 Qwen3-TTS 的文本转语音 Web 应用，支持自定义语音、语音设计和语音克隆，提供直观的 Web 界面。
> 这是一个非官方项目。如需查看官方 Qwen3-TTS 仓库，请访问 [QwenLM/Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS)。
[English Documentation](./README.md) [English Documentation](./README.md)
@@ -48,41 +50,173 @@
## 技术栈 ## 技术栈
后端：FastAPI + SQLAlchemy + PyTorch + JWT **后端**: FastAPI + SQLAlchemy + PyTorch + JWT
前端：React 19 + TypeScript + Vite + Tailwind + Shadcn/ui - 使用 PyTorch 直接推理 Qwen3-TTS 模型
- 异步任务处理与批量优化
- 支持本地模型 + 阿里云 API 双后端
## 快速开始 **前端**: React 19 + TypeScript + Vite + Tailwind + Shadcn/ui
### 后端 ## 安装部署
### 环境要求
- Python 3.9+ 并支持 CUDA（用于本地模型推理）
- Node.js 18+（用于前端）
- Git
### 1. 克隆仓库
```bash
git clone https://github.com/yourusername/Qwen3-TTS-webUI.git
cd Qwen3-TTS-webUI
```
### 2. 下载模型
**重要**: 模型**不会**自动下载，需要手动下载。
详细信息请访问官方仓库：[Qwen3-TTS 模型](https://github.com/QwenLM/Qwen3-TTS)
进入后端目录：
```bash
cd qwen3-tts-backend
mkdir -p Qwen && cd Qwen
```
**方式一：通过 ModelScope 下载（推荐中国大陆用户）**
```bash
pip install -U modelscope
modelscope download --model Qwen/Qwen3-TTS-Tokenizer-12Hz --local_dir ./Qwen3-TTS-Tokenizer-12Hz
modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --local_dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice
modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --local_dir ./Qwen3-TTS-12Hz-1.7B-VoiceDesign
modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-Base --local_dir ./Qwen3-TTS-12Hz-1.7B-Base
```
可选的 0.6B 模型（更小、更快）：
```bash
modelscope download --model Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice --local_dir ./Qwen3-TTS-12Hz-0.6B-CustomVoice
modelscope download --model Qwen/Qwen3-TTS-12Hz-0.6B-Base --local_dir ./Qwen3-TTS-12Hz-0.6B-Base
```
**方式二：通过 Hugging Face 下载**
```bash
pip install -U "huggingface_hub[cli]"
huggingface-cli download Qwen/Qwen3-TTS-Tokenizer-12Hz --local-dir ./Qwen3-TTS-Tokenizer-12Hz
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --local-dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --local-dir ./Qwen3-TTS-12Hz-1.7B-VoiceDesign
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-Base --local-dir ./Qwen3-TTS-12Hz-1.7B-Base
```
可选的 0.6B 模型（更小、更快）：
```bash
huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice --local-dir ./Qwen3-TTS-12Hz-0.6B-CustomVoice
huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-Base --local-dir ./Qwen3-TTS-12Hz-0.6B-Base
```
**最终目录结构：**
```
Qwen3-TTS-webUI/
├── qwen3-tts-backend/
│ └── Qwen/
│ ├── Qwen3-TTS-Tokenizer-12Hz/
│ ├── Qwen3-TTS-12Hz-1.7B-CustomVoice/
│ ├── Qwen3-TTS-12Hz-1.7B-VoiceDesign/
│ └── Qwen3-TTS-12Hz-1.7B-Base/
```
### 3. 后端配置
```bash ```bash
cd qwen3-tts-backend cd qwen3-tts-backend
# 创建虚拟环境
python -m venv venv python -m venv venv
source venv/bin/activate source venv/bin/activate # Windows: venv\Scripts\activate
# 安装依赖
pip install -r requirements.txt pip install -r requirements.txt
# 安装 Qwen3-TTS
pip install qwen-tts
# 创建配置文件
cp .env.example .env cp .env.example .env
# 编辑 .env 配置 MODEL_BASE_PATH 和 DEFAULT_BACKEND
# 本地模型：确保 MODEL_BASE_PATH 指向 Qwen 模型目录 # 编辑配置文件
# 阿里云：设置 DEFAULT_BACKEND=aliyun 并在 Web 设置页面配置 API 密钥 # 本地模型：设置 MODEL_BASE_PATH=./Qwen
uvicorn main:app --host 0.0.0.0 --port 8000 --reload # 仅阿里云 API：设置 DEFAULT_BACKEND=aliyun
nano .env # 或使用其他编辑器
``` ```
### 前端 **重要的后端配置** (`.env` 文件)：
```env
MODEL_DEVICE=cuda:0 # 使用 GPU（或 cpu 使用 CPU）
MODEL_BASE_PATH=./Qwen # 已下载模型的路径
DEFAULT_BACKEND=local # 使用本地模型用 'local'，API 用 'aliyun'
DATABASE_URL=sqlite:///./qwen_tts.db
SECRET_KEY=your-secret-key-here # 请修改此项！
```
启动后端服务：
```bash
# 使用 uvicorn 直接启动
uvicorn main:app --host 0.0.0.0 --port 8000 --reload
# 或使用 conda（如果你喜欢）
conda run -n qwen3-tts uvicorn main:app --host 0.0.0.0 --port 8000 --reload
```
验证后端是否运行：
```bash
curl http://127.0.0.1:8000/health
```
### 4. 前端配置
```bash ```bash
cd qwen3-tts-frontend cd qwen3-tts-frontend
# 安装依赖
npm install npm install
# 创建配置文件
cp .env.example .env cp .env.example .env
# 编辑 .env 配置 VITE_API_URL
# 编辑 .env 设置后端地址
echo "VITE_API_URL=http://localhost:8000" > .env
# 启动开发服务器
npm run dev npm run dev
``` ```
访问 `http://localhost:5173` ### 5. 访问应用
**首次运行**: 第一次运行时会自动初始化一个超级管理员账户： 在浏览器中打开：`http://localhost:5173`
**默认账号**：
- 用户名：`admin` - 用户名：`admin`
- 密码：`admin123456` - 密码：`admin123456`
- **重要**: 强烈建议登录后立刻修改密码！ - **重要**: 登录后请立即修改密码！
### 生产环境部署
用于生产环境：
```bash
# 后端：使用 gunicorn 或类似的 WSGI 服务器
cd qwen3-tts-backend
gunicorn main:app -w 4 -k uvicorn.workers.UvicornWorker -b 0.0.0.0:8000
# 前端：构建静态文件
cd qwen3-tts-frontend
npm run build
# 使用 nginx 或其他 Web 服务器提供 'dist' 文件夹
```
## 配置 ## 配置
@@ -164,6 +298,10 @@ GET /jobs/{id}/download - 下载结果
- `backend: "aliyun"` - 使用阿里云 TTS API - `backend: "aliyun"` - 使用阿里云 TTS API
- 如果不指定，则使用用户的默认后端设置 - 如果不指定，则使用用户的默认后端设置
## 特别鸣谢
本项目基于阿里云 Qwen 团队开源的 [Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS) 官方仓库构建。特别感谢 Qwen 团队开源如此强大的文本转语音模型。
## 许可证 ## 许可证
Apache-2.0 license Apache-2.0 license