Deploy Genie TTS
Browse files- .gitignore +196 -0
- DEPLOYMENT.md +151 -0
- PROJECT_SUMMARY.md +118 -0
- README.md.space +18 -0
- app.py +539 -0
- guidance.md +67 -0
- requirements.txt +40 -0
.gitignore
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Byte-compiled / optimized / DLL files
|
| 2 |
+
__pycache__/
|
| 3 |
+
*.py[cod]
|
| 4 |
+
*$py.class
|
| 5 |
+
|
| 6 |
+
# C extensions
|
| 7 |
+
*.so
|
| 8 |
+
|
| 9 |
+
# Distribution / packaging
|
| 10 |
+
.Python
|
| 11 |
+
build/
|
| 12 |
+
develop-eggs/
|
| 13 |
+
dist/
|
| 14 |
+
downloads/
|
| 15 |
+
eggs/
|
| 16 |
+
.eggs/
|
| 17 |
+
lib/
|
| 18 |
+
lib64/
|
| 19 |
+
parts/
|
| 20 |
+
sdist/
|
| 21 |
+
var/
|
| 22 |
+
wheels/
|
| 23 |
+
share/python-wheels/
|
| 24 |
+
*.egg-info/
|
| 25 |
+
.installed.cfg
|
| 26 |
+
*.egg
|
| 27 |
+
MANIFEST
|
| 28 |
+
|
| 29 |
+
# PyInstaller
|
| 30 |
+
# Usually these files are written by a python script from a template
|
| 31 |
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
| 32 |
+
*.manifest
|
| 33 |
+
*.spec
|
| 34 |
+
|
| 35 |
+
# Installer logs
|
| 36 |
+
pip-log.txt
|
| 37 |
+
pip-delete-this-directory.txt
|
| 38 |
+
|
| 39 |
+
# Unit test / coverage reports
|
| 40 |
+
htmlcov/
|
| 41 |
+
.tox/
|
| 42 |
+
.nox/
|
| 43 |
+
.coverage
|
| 44 |
+
.coverage.*
|
| 45 |
+
.cache
|
| 46 |
+
nosetests.xml
|
| 47 |
+
coverage.xml
|
| 48 |
+
*.cover
|
| 49 |
+
*.py,cover
|
| 50 |
+
.hypothesis/
|
| 51 |
+
.pytest_cache/
|
| 52 |
+
cover/
|
| 53 |
+
|
| 54 |
+
# Translations
|
| 55 |
+
*.mo
|
| 56 |
+
*.pot
|
| 57 |
+
|
| 58 |
+
# Django stuff:
|
| 59 |
+
*.log
|
| 60 |
+
local_settings.py
|
| 61 |
+
db.sqlite3
|
| 62 |
+
db.sqlite3-journal
|
| 63 |
+
|
| 64 |
+
# Flask stuff:
|
| 65 |
+
instance/
|
| 66 |
+
.webassets-cache
|
| 67 |
+
|
| 68 |
+
# Scrapy stuff:
|
| 69 |
+
.scrapy
|
| 70 |
+
|
| 71 |
+
# Sphinx documentation
|
| 72 |
+
docs/_build/
|
| 73 |
+
|
| 74 |
+
# PyBuilder
|
| 75 |
+
.pybuilder/
|
| 76 |
+
target/
|
| 77 |
+
|
| 78 |
+
# Jupyter Notebook
|
| 79 |
+
.ipynb_checkpoints
|
| 80 |
+
|
| 81 |
+
# IPython
|
| 82 |
+
profile_default/
|
| 83 |
+
ipython_config.py
|
| 84 |
+
|
| 85 |
+
# pyenv
|
| 86 |
+
# For a library or package, you might want to ignore these files since the code is
|
| 87 |
+
# intended to run in multiple environments; otherwise, check them in:
|
| 88 |
+
# .python-version
|
| 89 |
+
|
| 90 |
+
# pipenv
|
| 91 |
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
| 92 |
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
| 93 |
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
| 94 |
+
# install all needed dependencies.
|
| 95 |
+
#Pipfile.lock
|
| 96 |
+
|
| 97 |
+
# poetry
|
| 98 |
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
| 99 |
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
| 100 |
+
# commonly ignored for libraries.
|
| 101 |
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
| 102 |
+
#poetry.lock
|
| 103 |
+
|
| 104 |
+
# pdm
|
| 105 |
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
| 106 |
+
#pdm.lock
|
| 107 |
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
| 108 |
+
# in version control.
|
| 109 |
+
# https://pdm.fming.dev/#use-with-ide
|
| 110 |
+
.pdm.toml
|
| 111 |
+
|
| 112 |
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
| 113 |
+
__pypackages__/
|
| 114 |
+
|
| 115 |
+
# Celery stuff
|
| 116 |
+
celerybeat-schedule
|
| 117 |
+
celerybeat.pid
|
| 118 |
+
|
| 119 |
+
# SageMath parsed files
|
| 120 |
+
*.sage.py
|
| 121 |
+
|
| 122 |
+
# Environments
|
| 123 |
+
.env
|
| 124 |
+
.venv
|
| 125 |
+
env/
|
| 126 |
+
venv/
|
| 127 |
+
ENV/
|
| 128 |
+
env.bak/
|
| 129 |
+
venv.bak/
|
| 130 |
+
|
| 131 |
+
# Spyder project settings
|
| 132 |
+
.spyderproject
|
| 133 |
+
.spyproject
|
| 134 |
+
|
| 135 |
+
# Rope project settings
|
| 136 |
+
.ropeproject
|
| 137 |
+
|
| 138 |
+
# mkdocs documentation
|
| 139 |
+
/site
|
| 140 |
+
|
| 141 |
+
# mypy
|
| 142 |
+
.mypy_cache/
|
| 143 |
+
.dmypy.json
|
| 144 |
+
dmypy.json
|
| 145 |
+
|
| 146 |
+
# Pyre type checker
|
| 147 |
+
.pyre/
|
| 148 |
+
|
| 149 |
+
# pytype static type analyzer
|
| 150 |
+
.pytype/
|
| 151 |
+
|
| 152 |
+
# Cython debug symbols
|
| 153 |
+
cython_debug/
|
| 154 |
+
|
| 155 |
+
# Hugging Face specific
|
| 156 |
+
.cache/
|
| 157 |
+
huggingface_hub/
|
| 158 |
+
models/
|
| 159 |
+
checkpoints/
|
| 160 |
+
|
| 161 |
+
# Model and audio cache files
|
| 162 |
+
*.wav
|
| 163 |
+
*.mp3
|
| 164 |
+
*.onnx
|
| 165 |
+
*.bin
|
| 166 |
+
*.pth
|
| 167 |
+
*.ckpt
|
| 168 |
+
|
| 169 |
+
# Temporary files
|
| 170 |
+
tmp/
|
| 171 |
+
temp/
|
| 172 |
+
*.tmp
|
| 173 |
+
|
| 174 |
+
# OS specific
|
| 175 |
+
.DS_Store
|
| 176 |
+
.DS_Store?
|
| 177 |
+
._*
|
| 178 |
+
.Spotlight-V100
|
| 179 |
+
.Trashes
|
| 180 |
+
ehthumbs.db
|
| 181 |
+
Thumbs.db
|
| 182 |
+
|
| 183 |
+
# IDE
|
| 184 |
+
.vscode/
|
| 185 |
+
.idea/
|
| 186 |
+
*.swp
|
| 187 |
+
*.swo
|
| 188 |
+
*~
|
| 189 |
+
|
| 190 |
+
# Log files
|
| 191 |
+
*.log
|
| 192 |
+
logs/
|
| 193 |
+
|
| 194 |
+
# Gradio temporary files
|
| 195 |
+
gradio_cached_examples/
|
| 196 |
+
flagged/
|
DEPLOYMENT.md
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Hugging Face Space 部署指南
|
| 2 |
+
|
| 3 |
+
## 📋 准备工作
|
| 4 |
+
|
| 5 |
+
确保您已经有以下文件:
|
| 6 |
+
- `app.py` - 主要的 Gradio 应用
|
| 7 |
+
- `requirements.txt` - Python 依赖
|
| 8 |
+
- `README.md` - 项目说明文档
|
| 9 |
+
- `.gitignore` - Git 忽略文件
|
| 10 |
+
- `README.md.space` - Hugging Face Space 配置(需要重命名为 README.md)
|
| 11 |
+
|
| 12 |
+
## 🚀 部署步骤
|
| 13 |
+
|
| 14 |
+
### 1. 创建 Hugging Face Space
|
| 15 |
+
|
| 16 |
+
1. 登录 [Hugging Face](https://huggingface.co/)
|
| 17 |
+
2. 点击您的头像 → "New Space"
|
| 18 |
+
3. 填写 Space 信息:
|
| 19 |
+
- **Space name**: `GENIE` (或其他您喜欢的名称)
|
| 20 |
+
- **License**: MIT
|
| 21 |
+
- **SDK**: Gradio
|
| 22 |
+
- **Hardware**: CPU (免费) 或 GPU (付费)
|
| 23 |
+
- **Visibility**: Public
|
| 24 |
+
|
| 25 |
+
### 2. 上传文件
|
| 26 |
+
|
| 27 |
+
有两种方式上传文件:
|
| 28 |
+
|
| 29 |
+
#### 方式 A: Git 上传(推荐)
|
| 30 |
+
```bash
|
| 31 |
+
# 1. 克隆您创建的 Space
|
| 32 |
+
git clone https://huggingface.co/spaces/YOUR_USERNAME/GENIE
|
| 33 |
+
cd GENIE
|
| 34 |
+
|
| 35 |
+
# 2. 复制所有文件到此目录
|
| 36 |
+
# 将 README.md.space 重命名为 README.md(会替换默认的)
|
| 37 |
+
|
| 38 |
+
# 3. 提交并推送
|
| 39 |
+
git add .
|
| 40 |
+
git commit -m "Initial Genie TTS deployment"
|
| 41 |
+
git push
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
#### 方式 B: Web 界面上传
|
| 45 |
+
1. 在 Space 页面点击 "Files" 标签
|
| 46 |
+
2. 点击 "Add file" → "Upload file"
|
| 47 |
+
3. 上传所有必要文件
|
| 48 |
+
4. 将 `README.md.space` 的内容复制到默认的 `README.md` 中
|
| 49 |
+
|
| 50 |
+
### 3. 配置 Space
|
| 51 |
+
|
| 52 |
+
确保 README.md 文件开头包含正确的 YAML 元数据:
|
| 53 |
+
|
| 54 |
+
```yaml
|
| 55 |
+
---
|
| 56 |
+
title: 🔮 Genie TTS - AI语音合成
|
| 57 |
+
emoji: 🎵
|
| 58 |
+
colorFrom: purple
|
| 59 |
+
colorTo: pink
|
| 60 |
+
sdk: gradio
|
| 61 |
+
sdk_version: 4.44.0
|
| 62 |
+
app_file: app.py
|
| 63 |
+
pinned: false
|
| 64 |
+
license: mit
|
| 65 |
+
short_description: 基于Genie的日语文本转语音系统
|
| 66 |
+
tags:
|
| 67 |
+
- text-to-speech
|
| 68 |
+
- japanese
|
| 69 |
+
- gpt-sovits
|
| 70 |
+
- audio
|
| 71 |
+
- ai
|
| 72 |
+
- tts
|
| 73 |
+
- voice-synthesis
|
| 74 |
+
---
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
### 4. 等待构建
|
| 78 |
+
|
| 79 |
+
- Space 将自动开始构建
|
| 80 |
+
- 首次构建可能需要 5-10 分钟
|
| 81 |
+
- 您可以在 "Logs" 标签中查看构建进度
|
| 82 |
+
|
| 83 |
+
### 5. 测试应用
|
| 84 |
+
|
| 85 |
+
1. 构建完成后,访问您的 Space
|
| 86 |
+
2. 测试基本功能:
|
| 87 |
+
- 选择角色 "misono_mika"
|
| 88 |
+
- 输入日语文本,例如:"おはようございます"
|
| 89 |
+
- 点击 "开始合成"
|
| 90 |
+
- 等待音频生成
|
| 91 |
+
|
| 92 |
+
## ⚠️ 注意事项
|
| 93 |
+
|
| 94 |
+
### 性能考虑
|
| 95 |
+
- **首次运行**: 需要下载约 200MB 的模型文件,可能需要 30-60 秒
|
| 96 |
+
- **后续使用**: 模型会被缓存,合成速度较快(5-15 秒)
|
| 97 |
+
- **并发限制**: 免费 CPU 硬件建议限制并发用户数
|
| 98 |
+
|
| 99 |
+
### 内存管理
|
| 100 |
+
- Genie TTS 需要约 500MB-1GB RAM
|
| 101 |
+
- 如果遇到内存不足错误,考虑升级到付费硬件
|
| 102 |
+
|
| 103 |
+
### 错误排查
|
| 104 |
+
|
| 105 |
+
1. **依赖安装错误**
|
| 106 |
+
- 检查 `requirements.txt` 中的版本冲突
|
| 107 |
+
- 查看构建日志中的错误信息
|
| 108 |
+
|
| 109 |
+
2. **模型下载失败**
|
| 110 |
+
- 通常是网络问题,等待几分钟后重试
|
| 111 |
+
- 检查 Hugging Face Hub 的连接状态
|
| 112 |
+
|
| 113 |
+
3. **音频生成失败**
|
| 114 |
+
- 检查输入文本是否为日语
|
| 115 |
+
- 验证文本长度不超过 500 字符
|
| 116 |
+
|
| 117 |
+
## 🔧 高级配置
|
| 118 |
+
|
| 119 |
+
### 自定义硬件
|
| 120 |
+
如果需要更好的性能,可以升级硬件:
|
| 121 |
+
- **CPU Upgrade**: 更快的处理速度
|
| 122 |
+
- **GPU T4**: 显著提升推理速度(需要付费)
|
| 123 |
+
|
| 124 |
+
### 环境变量
|
| 125 |
+
在 Space 设置中添加环境变量:
|
| 126 |
+
```
|
| 127 |
+
HF_HUB_ENABLE_PROGRESS_BAR=1
|
| 128 |
+
TOKENIZERS_PARALLELISM=false
|
| 129 |
+
```
|
| 130 |
+
|
| 131 |
+
### 域名和访问
|
| 132 |
+
- Space URL: `https://huggingface.co/spaces/YOUR_USERNAME/GENIE`
|
| 133 |
+
- 可以申请自定义域名(Pro 功能)
|
| 134 |
+
|
| 135 |
+
## 📊 监控和维护
|
| 136 |
+
|
| 137 |
+
- 查看 Space 使用统计
|
| 138 |
+
- 监控错误日志
|
| 139 |
+
- 定期更新依赖包
|
| 140 |
+
- 根据用户反馈优化功能
|
| 141 |
+
|
| 142 |
+
## 🤝 社区分享
|
| 143 |
+
|
| 144 |
+
部署成功后,您可以:
|
| 145 |
+
- 在社交媒体分享您的 Space
|
| 146 |
+
- 在相关社区发布
|
| 147 |
+
- 收集用户反馈并持续改进
|
| 148 |
+
|
| 149 |
+
---
|
| 150 |
+
|
| 151 |
+
祝您部署成功!如有问题,可以参考 [Hugging Face Spaces 官方文档](https://huggingface.co/docs/hub/spaces)。
|
PROJECT_SUMMARY.md
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# 🎯 项目完成总结
|
| 2 |
+
|
| 3 |
+
## ✅ 已完成的工作
|
| 4 |
+
|
| 5 |
+
我已经为您成功创建了一个完整的 Hugging Face Spaces 部署方案,将 Genie TTS 模型部署为 Web 应用。
|
| 6 |
+
|
| 7 |
+
### 📁 文件结构
|
| 8 |
+
```
|
| 9 |
+
genie/
|
| 10 |
+
├── app.py # 主要的 Gradio 应用文件
|
| 11 |
+
├── requirements.txt # Python 依赖包列表
|
| 12 |
+
├── README.md # 项目说明文档
|
| 13 |
+
├── README.md.space # Hugging Face Space 配置文件
|
| 14 |
+
├── .gitignore # Git 忽略文件配置
|
| 15 |
+
├── DEPLOYMENT.md # 详细部署指南
|
| 16 |
+
└── PROJECT_SUMMARY.md # 项目总结(本文件)
|
| 17 |
+
```
|
| 18 |
+
|
| 19 |
+
### 🔧 核心功能实现
|
| 20 |
+
|
| 21 |
+
#### 1. Gradio Web 界面 (`app.py`)
|
| 22 |
+
- **多标签页设计**: 语音合成、示例教程、项目信息
|
| 23 |
+
- **智能角色管理**: 自动加载预训练角色模型
|
| 24 |
+
- **进度显示**: 实时显示模型加载和合成进度
|
| 25 |
+
- **错误处理**: 友好的错误提示和重试机制
|
| 26 |
+
- **音频输出**: 支持在线播放和下载
|
| 27 |
+
- **示例库**: 内置多个日语示例文本
|
| 28 |
+
|
| 29 |
+
#### 2. 依赖管理 (`requirements.txt`)
|
| 30 |
+
- **核心包**: genie-tts, gradio, torch
|
| 31 |
+
- **音频处理**: librosa, soundfile, scipy
|
| 32 |
+
- **模型推理**: onnxruntime
|
| 33 |
+
- **Hugging Face 集成**: huggingface-hub, transformers
|
| 34 |
+
- **系统监控**: psutil, rich
|
| 35 |
+
|
| 36 |
+
#### 3. 模型管理系统
|
| 37 |
+
- **自动下载**: 首次使用自动从 Hugging Face 下载模型
|
| 38 |
+
- **缓存机制**: 智能缓存管理,避免重复下载
|
| 39 |
+
- **内存优化**: LRU 缓存和资源清理
|
| 40 |
+
- **错误恢复**: 网络错误重试和失败处理
|
| 41 |
+
|
| 42 |
+
#### 4. 文本处理优化
|
| 43 |
+
- **预处理**: 自动文本清理和标点符号规范化
|
| 44 |
+
- **长度限制**: 防止过长文本导致的问题
|
| 45 |
+
- **编码处理**: 正确处理日语字符编码
|
| 46 |
+
- **分句支持**: 自动分句处理长文本
|
| 47 |
+
|
| 48 |
+
### 🌟 应用特色
|
| 49 |
+
|
| 50 |
+
1. **用户友好界面**
|
| 51 |
+
- 现代化设计,响应式布局
|
| 52 |
+
- 多标签页组织,信息层次清晰
|
| 53 |
+
- 实时进度反馈和状态显示
|
| 54 |
+
- 丰富的示例和使用指南
|
| 55 |
+
|
| 56 |
+
2. **性能优化**
|
| 57 |
+
- CPU 优化推理,无需 GPU
|
| 58 |
+
- 智能缓存管理
|
| 59 |
+
- 内存使用监控
|
| 60 |
+
- 异常处理和资源清理
|
| 61 |
+
|
| 62 |
+
3. **部署友好**
|
| 63 |
+
- 完整的依赖声明
|
| 64 |
+
- 环境变量配置
|
| 65 |
+
- 详细的部署指南
|
| 66 |
+
- Git 版本控制支持
|
| 67 |
+
|
| 68 |
+
## 🚀 部署步骤
|
| 69 |
+
|
| 70 |
+
### 快速部署
|
| 71 |
+
1. 访问 [Hugging Face Spaces](https://huggingface.co/spaces)
|
| 72 |
+
2. 创建新的 Space,选择 Gradio SDK
|
| 73 |
+
3. 上传所有文件(将 `README.md.space` 重命名为 `README.md`)
|
| 74 |
+
4. 等待自动构建完成
|
| 75 |
+
|
| 76 |
+
### 详细步骤
|
| 77 |
+
请参考 `DEPLOYMENT.md` 文件中的详细指南。
|
| 78 |
+
|
| 79 |
+
## 📊 预期性能
|
| 80 |
+
|
| 81 |
+
- **首次启动**: 30-60秒(下载模型)
|
| 82 |
+
- **后续合成**: 5-15秒每段文本
|
| 83 |
+
- **内存需求**: ~500MB RAM
|
| 84 |
+
- **存储需求**: ~200MB(模型文件)
|
| 85 |
+
|
| 86 |
+
## 🎯 支持功能
|
| 87 |
+
|
| 88 |
+
- ✅ 日语文本转语音
|
| 89 |
+
- ✅ 预训练角色 (misono_mika)
|
| 90 |
+
- ✅ 实时音频播放
|
| 91 |
+
- ✅ 音频文件下载
|
| 92 |
+
- ✅ 示例文本库
|
| 93 |
+
- ✅ 错误处理和重试
|
| 94 |
+
- ✅ 响应式 Web 界面
|
| 95 |
+
|
| 96 |
+
## 🔮 未来扩展
|
| 97 |
+
|
| 98 |
+
可以考虑的功能扩展:
|
| 99 |
+
- 添加更多预训练角色
|
| 100 |
+
- 支持中文和英文TTS
|
| 101 |
+
- 批量文本处理
|
| 102 |
+
- 语音风格调节
|
| 103 |
+
- API 接口支持
|
| 104 |
+
|
| 105 |
+
## ⚠️ 注意事项
|
| 106 |
+
|
| 107 |
+
1. **首次使用**: 需要下载模型文件,请确保网络连接稳定
|
| 108 |
+
2. **文本限制**: 目前主要支持日语,建议文本长度控制在500字符以内
|
| 109 |
+
3. **并发限制**: 免费版 Hugging Face Spaces 有并发限制
|
| 110 |
+
4. **模型版本**: 基于 GPT-SoVITS V2,支持高质量语音合成
|
| 111 |
+
|
| 112 |
+
## 🎉 部署成功!
|
| 113 |
+
|
| 114 |
+
您现在可以按照 `DEPLOYMENT.md` 中的指南将此应用部署到 Hugging Face Spaces 上。部署成功后,用户可以通过 Web 界面轻松使用 Genie TTS 进行日语语音合成。
|
| 115 |
+
|
| 116 |
+
---
|
| 117 |
+
|
| 118 |
+
**祝您部署顺利!如有任何问题,请参考相关文档或联系开发者。** 🚀
|
README.md.space
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
title: 🔮 Genie TTS - AI语音合成
|
| 2 |
+
emoji: 🎵
|
| 3 |
+
colorFrom: purple
|
| 4 |
+
colorTo: pink
|
| 5 |
+
sdk: gradio
|
| 6 |
+
sdk_version: 4.44.0
|
| 7 |
+
app_file: app.py
|
| 8 |
+
pinned: false
|
| 9 |
+
license: mit
|
| 10 |
+
short_description: 基于Genie的日语文本转语音系统
|
| 11 |
+
tags:
|
| 12 |
+
- text-to-speech
|
| 13 |
+
- japanese
|
| 14 |
+
- gpt-sovits
|
| 15 |
+
- audio
|
| 16 |
+
- ai
|
| 17 |
+
- tts
|
| 18 |
+
- voice-synthesis
|
app.py
ADDED
|
@@ -0,0 +1,539 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
import os
|
| 3 |
+
import tempfile
|
| 4 |
+
import logging
|
| 5 |
+
import warnings
|
| 6 |
+
import subprocess
|
| 7 |
+
import sys
|
| 8 |
+
from pathlib import Path
|
| 9 |
+
|
| 10 |
+
# 设置日志
|
| 11 |
+
logging.basicConfig(level=logging.INFO)
|
| 12 |
+
logger = logging.getLogger(__name__)
|
| 13 |
+
|
| 14 |
+
# 禁用一些警告
|
| 15 |
+
warnings.filterwarnings("ignore", category=FutureWarning)
|
| 16 |
+
warnings.filterwarnings("ignore", category=UserWarning)
|
| 17 |
+
|
| 18 |
+
def install_genie_tts():
|
| 19 |
+
"""安装genie-tts包"""
|
| 20 |
+
try:
|
| 21 |
+
import genie_tts
|
| 22 |
+
logger.info("genie-tts已安装")
|
| 23 |
+
return True
|
| 24 |
+
except ImportError:
|
| 25 |
+
logger.info("正在安装genie-tts...")
|
| 26 |
+
try:
|
| 27 |
+
subprocess.check_call([sys.executable, "-m", "pip", "install", "genie-tts"])
|
| 28 |
+
import genie_tts
|
| 29 |
+
logger.info("genie-tts安装成功")
|
| 30 |
+
return True
|
| 31 |
+
except Exception as e:
|
| 32 |
+
logger.error(f"安装genie-tts失败: {e}")
|
| 33 |
+
return False
|
| 34 |
+
|
| 35 |
+
# 安装Genie TTS
|
| 36 |
+
install_success = install_genie_tts()
|
| 37 |
+
|
| 38 |
+
if install_success:
|
| 39 |
+
try:
|
| 40 |
+
import genie_tts as genie
|
| 41 |
+
logger.info("Genie TTS导入成功")
|
| 42 |
+
except ImportError as e:
|
| 43 |
+
logger.error(f"导入Genie TTS失败: {e}")
|
| 44 |
+
genie = None
|
| 45 |
+
else:
|
| 46 |
+
genie = None
|
| 47 |
+
|
| 48 |
+
class GenieTTSInterface:
|
| 49 |
+
def __init__(self):
|
| 50 |
+
self.available_characters = ['misono_mika'] # 预定义角色
|
| 51 |
+
self.current_character = None
|
| 52 |
+
self.model_cache_dir = self.setup_cache_directory()
|
| 53 |
+
self.is_initialized = False
|
| 54 |
+
|
| 55 |
+
def setup_cache_directory(self):
|
| 56 |
+
"""设置模型缓存目录"""
|
| 57 |
+
cache_dir = os.path.join(tempfile.gettempdir(), "genie_tts_cache")
|
| 58 |
+
os.makedirs(cache_dir, exist_ok=True)
|
| 59 |
+
return cache_dir
|
| 60 |
+
|
| 61 |
+
def check_model_availability(self, character_name):
|
| 62 |
+
"""检查模型是否已缓存"""
|
| 63 |
+
model_files = [
|
| 64 |
+
'prompt.wav', 'prompt_wav.json',
|
| 65 |
+
't2s_encoder_fp32.onnx', 't2s_first_stage_decoder_fp32.onnx',
|
| 66 |
+
't2s_stage_decoder_fp32.onnx', 'vits_fp32.onnx'
|
| 67 |
+
]
|
| 68 |
+
|
| 69 |
+
character_cache_dir = os.path.join(self.model_cache_dir, character_name)
|
| 70 |
+
if not os.path.exists(character_cache_dir):
|
| 71 |
+
return False
|
| 72 |
+
|
| 73 |
+
for file_name in model_files:
|
| 74 |
+
if not os.path.exists(os.path.join(character_cache_dir, file_name)):
|
| 75 |
+
return False
|
| 76 |
+
return True
|
| 77 |
+
|
| 78 |
+
def initialize_genie(self):
|
| 79 |
+
"""初始化Genie TTS环境"""
|
| 80 |
+
if self.is_initialized:
|
| 81 |
+
return True
|
| 82 |
+
|
| 83 |
+
try:
|
| 84 |
+
# 设置环境变量以优化下载
|
| 85 |
+
os.environ["HF_HUB_ENABLE_PROGRESS_BAR"] = "1"
|
| 86 |
+
os.environ["TOKENIZERS_PARALLELISM"] = "false" # 避免警告
|
| 87 |
+
|
| 88 |
+
# 设置缓存目录
|
| 89 |
+
if hasattr(genie, '_internal'):
|
| 90 |
+
logger.info("Genie TTS环境初始化成功")
|
| 91 |
+
|
| 92 |
+
self.is_initialized = True
|
| 93 |
+
return True
|
| 94 |
+
|
| 95 |
+
except Exception as e:
|
| 96 |
+
logger.error(f"初始化Genie TTS失败: {e}")
|
| 97 |
+
return False
|
| 98 |
+
|
| 99 |
+
def load_character(self, character_name):
|
| 100 |
+
"""加载角色模型"""
|
| 101 |
+
if not genie:
|
| 102 |
+
return None, "Genie TTS未正确安装"
|
| 103 |
+
|
| 104 |
+
if not self.initialize_genie():
|
| 105 |
+
return None, "Genie TTS初始化失败"
|
| 106 |
+
|
| 107 |
+
try:
|
| 108 |
+
logger.info(f"正在加载角色: {character_name}")
|
| 109 |
+
|
| 110 |
+
# 检查模型是否已缓存
|
| 111 |
+
if self.check_model_availability(character_name):
|
| 112 |
+
logger.info(f"使用缓存的模型: {character_name}")
|
| 113 |
+
else:
|
| 114 |
+
logger.info(f"首次下载模型: {character_name},请稍候...")
|
| 115 |
+
|
| 116 |
+
# 加载预定义角色(这会自动处理下载)
|
| 117 |
+
genie.load_predefined_character(character_name)
|
| 118 |
+
self.current_character = character_name
|
| 119 |
+
|
| 120 |
+
return f"角色 {character_name} 加载成功!", ""
|
| 121 |
+
|
| 122 |
+
except Exception as e:
|
| 123 |
+
error_msg = str(e)
|
| 124 |
+
logger.error(f"加载角色失败: {error_msg}")
|
| 125 |
+
|
| 126 |
+
# 提供更友好的错误信息
|
| 127 |
+
if "network" in error_msg.lower() or "connection" in error_msg.lower():
|
| 128 |
+
return None, "网络连接错误,请检查网络连接后重试"
|
| 129 |
+
elif "disk space" in error_msg.lower():
|
| 130 |
+
return None, "磁盘空间不足,请清理空间后重试"
|
| 131 |
+
elif "timeout" in error_msg.lower():
|
| 132 |
+
return None, "下载超时,请重试"
|
| 133 |
+
else:
|
| 134 |
+
return None, f"加载角色失败: {error_msg}"
|
| 135 |
+
|
| 136 |
+
def estimate_download_size(self, character_name):
|
| 137 |
+
"""估算下载大小"""
|
| 138 |
+
# 基于Genie模型的实际大小
|
| 139 |
+
model_sizes = {
|
| 140 |
+
'misono_mika': 180 # MB
|
| 141 |
+
}
|
| 142 |
+
return model_sizes.get(character_name, 200)
|
| 143 |
+
|
| 144 |
+
def cleanup_cache(self):
|
| 145 |
+
"""清理缓存"""
|
| 146 |
+
try:
|
| 147 |
+
import shutil
|
| 148 |
+
if os.path.exists(self.model_cache_dir):
|
| 149 |
+
shutil.rmtree(self.model_cache_dir)
|
| 150 |
+
self.setup_cache_directory()
|
| 151 |
+
logger.info("缓存清理完成")
|
| 152 |
+
return True
|
| 153 |
+
except Exception as e:
|
| 154 |
+
logger.error(f"清理缓存失败: {e}")
|
| 155 |
+
return False
|
| 156 |
+
|
| 157 |
+
def synthesize_speech(self, text, character_name, play_audio=False):
|
| 158 |
+
"""文本转语音 - 增强版"""
|
| 159 |
+
if not genie:
|
| 160 |
+
return None, "Genie TTS未正确安装"
|
| 161 |
+
|
| 162 |
+
if not text.strip():
|
| 163 |
+
return None, "请输入要合成的文本"
|
| 164 |
+
|
| 165 |
+
# 文本长度检查
|
| 166 |
+
if len(text) > 500:
|
| 167 |
+
return None, "文本过长(超过500字符),请缩短文本长度"
|
| 168 |
+
|
| 169 |
+
if character_name != self.current_character:
|
| 170 |
+
status, error = self.load_character(character_name)
|
| 171 |
+
if error:
|
| 172 |
+
return None, error
|
| 173 |
+
|
| 174 |
+
try:
|
| 175 |
+
# 文本预处理
|
| 176 |
+
processed_text = self.preprocess_text(text)
|
| 177 |
+
|
| 178 |
+
# 创建临时文件保存音频
|
| 179 |
+
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp_file:
|
| 180 |
+
output_path = tmp_file.name
|
| 181 |
+
|
| 182 |
+
logger.info(f"正在合成语音: {processed_text[:50]}...")
|
| 183 |
+
|
| 184 |
+
# 设置内存限制环境变量
|
| 185 |
+
original_env = os.environ.get('PYTORCH_JIT_USE_NNC_NOT_NVFUSER', None)
|
| 186 |
+
os.environ['PYTORCH_JIT_USE_NNC_NOT_NVFUSER'] = '1'
|
| 187 |
+
|
| 188 |
+
try:
|
| 189 |
+
# 执行TTS
|
| 190 |
+
genie.tts(
|
| 191 |
+
character_name=character_name,
|
| 192 |
+
text=processed_text,
|
| 193 |
+
play=False, # 在服务器环境不播放
|
| 194 |
+
split_sentence=True,
|
| 195 |
+
save_path=output_path
|
| 196 |
+
)
|
| 197 |
+
finally:
|
| 198 |
+
# 恢复环境变量
|
| 199 |
+
if original_env is None and 'PYTORCH_JIT_USE_NNC_NOT_NVFUSER' in os.environ:
|
| 200 |
+
del os.environ['PYTORCH_JIT_USE_NNC_NOT_NVFUSER']
|
| 201 |
+
elif original_env is not None:
|
| 202 |
+
os.environ['PYTORCH_JIT_USE_NNC_NOT_NVFUSER'] = original_env
|
| 203 |
+
|
| 204 |
+
# 验证输出文件
|
| 205 |
+
if not os.path.exists(output_path):
|
| 206 |
+
return None, "语音合成失败:输出文件未生成"
|
| 207 |
+
|
| 208 |
+
file_size = os.path.getsize(output_path)
|
| 209 |
+
if file_size == 0:
|
| 210 |
+
return None, "语音合成失败:输出文件为空"
|
| 211 |
+
elif file_size < 1000: # 小于1KB可能是错误
|
| 212 |
+
return None, "语音合成失败:输出文件异常小"
|
| 213 |
+
|
| 214 |
+
logger.info(f"语音合成成功,文件大小: {file_size/1024:.1f}KB")
|
| 215 |
+
return output_path, ""
|
| 216 |
+
|
| 217 |
+
except Exception as e:
|
| 218 |
+
error_msg = str(e)
|
| 219 |
+
logger.error(f"语音合成失败: {error_msg}")
|
| 220 |
+
|
| 221 |
+
# 提供更详细的错误信息
|
| 222 |
+
if "out of memory" in error_msg.lower() or "memory" in error_msg.lower():
|
| 223 |
+
return None, "内存不足,请尝试缩短文本或重启应用"
|
| 224 |
+
elif "cuda" in error_msg.lower():
|
| 225 |
+
return None, "GPU相关错误,正在使用CPU模式重试"
|
| 226 |
+
elif "model" in error_msg.lower():
|
| 227 |
+
return None, "模型加载错误,请重新选择角色"
|
| 228 |
+
elif "timeout" in error_msg.lower():
|
| 229 |
+
return None, "处理超时,请尝试缩短文本"
|
| 230 |
+
else:
|
| 231 |
+
return None, f"语音合成失败: {error_msg}"
|
| 232 |
+
|
| 233 |
+
def preprocess_text(self, text):
|
| 234 |
+
"""文本预处理"""
|
| 235 |
+
# 基本清理
|
| 236 |
+
text = text.strip()
|
| 237 |
+
|
| 238 |
+
# 替换常见的问题字符
|
| 239 |
+
replacements = {
|
| 240 |
+
'"': '"',
|
| 241 |
+
'"': '"',
|
| 242 |
+
''': "'",
|
| 243 |
+
''': "'",
|
| 244 |
+
'—': '一',
|
| 245 |
+
'–': '-',
|
| 246 |
+
}
|
| 247 |
+
|
| 248 |
+
for old, new in replacements.items():
|
| 249 |
+
text = text.replace(old, new)
|
| 250 |
+
|
| 251 |
+
# 确保句子有适当的标点
|
| 252 |
+
if text and not text.endswith(('。', '!', '?', '.', '!', '?')):
|
| 253 |
+
text += '。'
|
| 254 |
+
|
| 255 |
+
return text
|
| 256 |
+
|
| 257 |
+
def get_system_info(self):
|
| 258 |
+
"""获取系统信息用于调试"""
|
| 259 |
+
try:
|
| 260 |
+
import psutil
|
| 261 |
+
memory = psutil.virtual_memory()
|
| 262 |
+
disk = psutil.disk_usage('/')
|
| 263 |
+
|
| 264 |
+
return {
|
| 265 |
+
'memory_total': f"{memory.total / (1024**3):.1f}GB",
|
| 266 |
+
'memory_available': f"{memory.available / (1024**3):.1f}GB",
|
| 267 |
+
'memory_percent': f"{memory.percent}%",
|
| 268 |
+
'disk_free': f"{disk.free / (1024**3):.1f}GB"
|
| 269 |
+
}
|
| 270 |
+
except:
|
| 271 |
+
return {"status": "无法获取系统信息"}
|
| 272 |
+
|
| 273 |
+
# 创建接口实例
|
| 274 |
+
tts_interface = GenieTTSInterface()
|
| 275 |
+
|
| 276 |
+
def create_interface():
|
| 277 |
+
"""创建Gradio界面"""
|
| 278 |
+
|
| 279 |
+
def tts_wrapper(text, character, progress=gr.Progress()):
|
| 280 |
+
"""TTS包装函数"""
|
| 281 |
+
if not text.strip():
|
| 282 |
+
return None, "❌ 请输入要合成的文本"
|
| 283 |
+
|
| 284 |
+
progress(0.1, desc="准备模型...")
|
| 285 |
+
|
| 286 |
+
# 加载字符模型
|
| 287 |
+
if character != tts_interface.current_character:
|
| 288 |
+
progress(0.3, desc=f"加载角色模型: {character}")
|
| 289 |
+
status, error = tts_interface.load_character(character)
|
| 290 |
+
if error:
|
| 291 |
+
return None, f"❌ {error}"
|
| 292 |
+
|
| 293 |
+
progress(0.5, desc="正在合成语音...")
|
| 294 |
+
|
| 295 |
+
audio_path, error = tts_interface.synthesize_speech(text, character)
|
| 296 |
+
|
| 297 |
+
progress(0.9, desc="完成处理...")
|
| 298 |
+
|
| 299 |
+
if error:
|
| 300 |
+
return None, f"❌ {error}"
|
| 301 |
+
|
| 302 |
+
progress(1.0, desc="✅ 合成成功!")
|
| 303 |
+
return audio_path, f"✅ 合成成功!音频长度: {get_audio_duration(audio_path):.1f}秒"
|
| 304 |
+
|
| 305 |
+
def get_audio_duration(audio_path):
|
| 306 |
+
"""获取音频时长"""
|
| 307 |
+
try:
|
| 308 |
+
import librosa
|
| 309 |
+
y, sr = librosa.load(audio_path, sr=None)
|
| 310 |
+
return len(y) / sr
|
| 311 |
+
except:
|
| 312 |
+
return 0
|
| 313 |
+
|
| 314 |
+
def clear_all():
|
| 315 |
+
"""清空所有输入和输出"""
|
| 316 |
+
return "", None, "🔄 已清空所有内容"
|
| 317 |
+
|
| 318 |
+
def load_example(text, character):
|
| 319 |
+
"""加载示例"""
|
| 320 |
+
return text, character, f"📝 已加载示例: {text[:20]}..."
|
| 321 |
+
|
| 322 |
+
# 定义界面
|
| 323 |
+
with gr.Blocks(
|
| 324 |
+
title="🔮 Genie TTS - 语音合成",
|
| 325 |
+
theme=gr.themes.Soft(),
|
| 326 |
+
css="""
|
| 327 |
+
.gradio-container {
|
| 328 |
+
max-width: 1200px !important;
|
| 329 |
+
}
|
| 330 |
+
.status-success {
|
| 331 |
+
color: #28a745 !important;
|
| 332 |
+
}
|
| 333 |
+
.status-error {
|
| 334 |
+
color: #dc3545 !important;
|
| 335 |
+
}
|
| 336 |
+
"""
|
| 337 |
+
) as demo:
|
| 338 |
+
gr.Markdown("""
|
| 339 |
+
# 🔮 Genie TTS - AI 语音合成系统
|
| 340 |
+
|
| 341 |
+
基于 [High-Logic/Genie](https://github.com/High-Logic/Genie) 的轻量级 TTS 推理引擎,支持高质量日语语音合成。
|
| 342 |
+
|
| 343 |
+
<div style="background: linear-gradient(90deg, #667eea 0%, #764ba2 100%); padding: 1rem; border-radius: 10px; color: white; margin: 1rem 0;">
|
| 344 |
+
<strong>🌟 功能特点</strong><br>
|
| 345 |
+
✅ CPU 优化推理,无需 GPU<br>
|
| 346 |
+
✅ 基于 GPT-SoVITS V2 技术<br>
|
| 347 |
+
✅ 支持长文本自动分句<br>
|
| 348 |
+
✅ 实时音频流输出
|
| 349 |
+
</div>
|
| 350 |
+
|
| 351 |
+
**📖 使用说明:** 选择角色模型 → 输入日语文本 → 点击合成按钮 → 获得高质量语音
|
| 352 |
+
""")
|
| 353 |
+
|
| 354 |
+
with gr.Tab("🎵 语音合成") as tts_tab:
|
| 355 |
+
with gr.Row():
|
| 356 |
+
with gr.Column(scale=1):
|
| 357 |
+
# 角色选择
|
| 358 |
+
with gr.Group():
|
| 359 |
+
gr.Markdown("### 👤 角色设置")
|
| 360 |
+
character_dropdown = gr.Dropdown(
|
| 361 |
+
choices=tts_interface.available_characters,
|
| 362 |
+
value="misono_mika",
|
| 363 |
+
label="🎭 选择角色",
|
| 364 |
+
info="当前可用的预训练角色模型",
|
| 365 |
+
interactive=True
|
| 366 |
+
)
|
| 367 |
+
|
| 368 |
+
# 文本输入
|
| 369 |
+
with gr.Group():
|
| 370 |
+
gr.Markdown("### 📝 文本输入")
|
| 371 |
+
text_input = gr.Textbox(
|
| 372 |
+
lines=5,
|
| 373 |
+
label="📄 输入文本",
|
| 374 |
+
placeholder="请输入要合成的日语文本...\n例如:どうしようかな……やっぱりやりたいかも……!",
|
| 375 |
+
info="💡 支持日语文本,建议输入完整的句子以获得更好的效果",
|
| 376 |
+
show_copy_button=True
|
| 377 |
+
)
|
| 378 |
+
|
| 379 |
+
# 控制按钮
|
| 380 |
+
with gr.Row():
|
| 381 |
+
submit_btn = gr.Button(
|
| 382 |
+
"🎵 开始合成",
|
| 383 |
+
variant="primary",
|
| 384 |
+
size="lg",
|
| 385 |
+
scale=2
|
| 386 |
+
)
|
| 387 |
+
clear_btn = gr.Button(
|
| 388 |
+
"🔄 清空",
|
| 389 |
+
variant="secondary",
|
| 390 |
+
scale=1
|
| 391 |
+
)
|
| 392 |
+
|
| 393 |
+
with gr.Column(scale=1):
|
| 394 |
+
# 音频输出
|
| 395 |
+
with gr.Group():
|
| 396 |
+
gr.Markdown("### 🔊 音频输出")
|
| 397 |
+
audio_output = gr.Audio(
|
| 398 |
+
label="🎶 生成的音频",
|
| 399 |
+
type="filepath",
|
| 400 |
+
interactive=False,
|
| 401 |
+
show_download_button=True
|
| 402 |
+
)
|
| 403 |
+
|
| 404 |
+
# 状态显示
|
| 405 |
+
status_output = gr.Textbox(
|
| 406 |
+
label="📊 合成状态",
|
| 407 |
+
interactive=False,
|
| 408 |
+
show_copy_button=False
|
| 409 |
+
)
|
| 410 |
+
|
| 411 |
+
# 示例和教程标签页
|
| 412 |
+
with gr.Tab("📚 示例与教程") as examples_tab:
|
| 413 |
+
gr.Markdown("### 🎯 快速示例")
|
| 414 |
+
gr.Markdown("点击下面的示例可以快速体验不同类型的文本合成效果:")
|
| 415 |
+
|
| 416 |
+
# 示例网格
|
| 417 |
+
with gr.Row():
|
| 418 |
+
with gr.Column():
|
| 419 |
+
gr.Markdown("**🌅 问候语**")
|
| 420 |
+
gr.Examples(
|
| 421 |
+
examples=[
|
| 422 |
+
["おはようございます!", "misono_mika"],
|
| 423 |
+
["こんにちは、元気ですか?", "misono_mika"],
|
| 424 |
+
["お疲れさまでした", "misono_mika"]
|
| 425 |
+
],
|
| 426 |
+
inputs=[text_input, character_dropdown],
|
| 427 |
+
outputs=[text_input, character_dropdown, status_output],
|
| 428 |
+
fn=load_example,
|
| 429 |
+
run_on_click=True
|
| 430 |
+
)
|
| 431 |
+
|
| 432 |
+
with gr.Column():
|
| 433 |
+
gr.Markdown("**💭 情感表达**")
|
| 434 |
+
gr.Examples(
|
| 435 |
+
examples=[
|
| 436 |
+
["どうしようかな……やっぱりやりたいかも……!", "misono_mika"],
|
| 437 |
+
["うーん、これは難しいですね", "misono_mika"],
|
| 438 |
+
["わあ、すごいですね!", "misono_mika"]
|
| 439 |
+
],
|
| 440 |
+
inputs=[text_input, character_dropdown],
|
| 441 |
+
outputs=[text_input, character_dropdown, status_output],
|
| 442 |
+
fn=load_example,
|
| 443 |
+
run_on_click=True
|
| 444 |
+
)
|
| 445 |
+
|
| 446 |
+
with gr.Column():
|
| 447 |
+
gr.Markdown("**🎭 日常对话**")
|
| 448 |
+
gr.Examples(
|
| 449 |
+
examples=[
|
| 450 |
+
["ありがとうございます", "misono_mika"],
|
| 451 |
+
["さようなら、また明日", "misono_mika"],
|
| 452 |
+
["お先に失礼します", "misono_mika"]
|
| 453 |
+
],
|
| 454 |
+
inputs=[text_input, character_dropdown],
|
| 455 |
+
outputs=[text_input, character_dropdown, status_output],
|
| 456 |
+
fn=load_example,
|
| 457 |
+
run_on_click=True
|
| 458 |
+
)
|
| 459 |
+
|
| 460 |
+
gr.Markdown("""
|
| 461 |
+
### 📋 使用技巧
|
| 462 |
+
|
| 463 |
+
1. **文本长度**: 建议单次输入文本长度在 100 字以内,过长的文本会自动分句处理
|
| 464 |
+
2. **标点符号**: 适当使用标点符号(。!?)可以改善语音的自然度
|
| 465 |
+
3. **特殊符号**: 支持省略号(……)和感叹号(!)等情感表达
|
| 466 |
+
4. **处理时间**: 首次加载角色需要下载模型(约30秒),后续合成较快(5-10秒)
|
| 467 |
+
|
| 468 |
+
### 🔧 技术说明
|
| 469 |
+
|
| 470 |
+
- **模型架构**: 基于 Transformer 的端到端语音合成
|
| 471 |
+
- **采样率**: 32kHz,支持高质量音频输出
|
| 472 |
+
- **推理方式**: CPU 优化的 ONNX 模型,适合云端部署
|
| 473 |
+
- **内存占用**: 约 500MB RAM,支持并发处理
|
| 474 |
+
""")
|
| 475 |
+
|
| 476 |
+
# 关于标签页
|
| 477 |
+
with gr.Tab("ℹ️ 关于项目") as about_tab:
|
| 478 |
+
gr.Markdown("""
|
| 479 |
+
### 🔍 项目信息
|
| 480 |
+
|
| 481 |
+
**Genie TTS** 是基于 GPT-SoVITS V2 架构的轻量级语音合成引擎,专门为 CPU 推理优化。
|
| 482 |
+
|
| 483 |
+
#### 📊 技术规格
|
| 484 |
+
|
| 485 |
+
| 项目 | 规格 |
|
| 486 |
+
|------|------|
|
| 487 |
+
| **基础模型** | GPT-SoVITS V2 |
|
| 488 |
+
| **推理框架** | ONNX Runtime |
|
| 489 |
+
| **支持语言** | 日语 (Japanese) |
|
| 490 |
+
| **音频格式** | WAV, 32kHz |
|
| 491 |
+
| **推理设备** | CPU (无需 GPU) |
|
| 492 |
+
| **模型大小** | ~200MB |
|
| 493 |
+
| **内存需求** | ~500MB RAM |
|
| 494 |
+
|
| 495 |
+
#### � 相关链接
|
| 496 |
+
|
| 497 |
+
- 🏠 [项目主页](https://github.com/High-Logic/Genie)
|
| 498 |
+
- 🤗 [Hugging Face 模型](https://huggingface.co/High-Logic/Genie)
|
| 499 |
+
- 📖 [GPT-SoVITS 官方](https://github.com/RVC-Boss/GPT-SoVITS)
|
| 500 |
+
- 💬 [问题反馈](https://github.com/High-Logic/Genie/issues)
|
| 501 |
+
|
| 502 |
+
#### 🙏 致谢
|
| 503 |
+
|
| 504 |
+
感谢以下项目和开发者:
|
| 505 |
+
- [High-Logic](https://github.com/High-Logic) 团队开发的 Genie TTS
|
| 506 |
+
- [RVC-Boss](https://github.com/RVC-Boss) 团队的 GPT-SoVITS 项目
|
| 507 |
+
- Hugging Face 提供的模型托管和 Spaces 平台
|
| 508 |
+
|
| 509 |
+
#### ⚖️ 免责声明
|
| 510 |
+
|
| 511 |
+
本应用仅用于演示和研究目的。请合理使用,生成的语音内容责任由使用者承担。
|
| 512 |
+
""")
|
| 513 |
+
|
| 514 |
+
# 绑定事件
|
| 515 |
+
submit_btn.click(
|
| 516 |
+
fn=tts_wrapper,
|
| 517 |
+
inputs=[text_input, character_dropdown],
|
| 518 |
+
outputs=[audio_output, status_output],
|
| 519 |
+
show_progress="full",
|
| 520 |
+
queue=True
|
| 521 |
+
)
|
| 522 |
+
|
| 523 |
+
clear_btn.click(
|
| 524 |
+
fn=clear_all,
|
| 525 |
+
outputs=[text_input, audio_output, status_output]
|
| 526 |
+
)
|
| 527 |
+
|
| 528 |
+
return demo
|
| 529 |
+
|
| 530 |
+
# 启动应用
|
| 531 |
+
if __name__ == "__main__":
|
| 532 |
+
demo = create_interface()
|
| 533 |
+
demo.launch(
|
| 534 |
+
server_name="0.0.0.0",
|
| 535 |
+
server_port=7860,
|
| 536 |
+
show_api=False,
|
| 537 |
+
show_error=True,
|
| 538 |
+
quiet=False
|
| 539 |
+
)
|
guidance.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Spaces
|
| 2 |
+
Hugging Face's logo
|
| 3 |
+
|
| 4 |
+
Tom1986
|
| 5 |
+
/
|
| 6 |
+
GENIE
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
like
|
| 10 |
+
0
|
| 11 |
+
|
| 12 |
+
Logs
|
| 13 |
+
App
|
| 14 |
+
Files
|
| 15 |
+
Community
|
| 16 |
+
Settings
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
🚀 Get started with your gradio Space!
|
| 20 |
+
Your new space has been created, follow these steps to get started (or read the full documentation)
|
| 21 |
+
|
| 22 |
+
Start by cloning this repo by using:
|
| 23 |
+
|
| 24 |
+
Use an access token as git password/credential
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
# When prompted for a password, use an access token with write permissions.
|
| 28 |
+
# Generate one from your settings: https://huggingface.co/settings/tokens
|
| 29 |
+
git clone https://huggingface.co/spaces/Tom1986/GENIE
|
| 30 |
+
|
| 31 |
+
# Make sure hf CLI is installed: pip install -U "huggingface_hub[cli]"
|
| 32 |
+
hf download Tom1986/GENIE --repo-type=space
|
| 33 |
+
Create your gradio app.py file:
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
import gradio as gr
|
| 37 |
+
|
| 38 |
+
def greet(name):
|
| 39 |
+
return "Hello " + name + "!!"
|
| 40 |
+
|
| 41 |
+
demo = gr.Interface(fn=greet, inputs="text", outputs="text")
|
| 42 |
+
demo.launch()
|
| 43 |
+
Then commit and push:
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
git add app.py
|
| 47 |
+
git commit -m "Add application file"
|
| 48 |
+
git push
|
| 49 |
+
Hint Alternatively, you can create the app.py file directly in your browser.
|
| 50 |
+
Finally, your Space should be running on this page after a few moments!
|
| 51 |
+
|
| 52 |
+
Dependencies
|
| 53 |
+
|
| 54 |
+
You can add a requirements.txt file at the root of the repository to specify Python dependencies
|
| 55 |
+
|
| 56 |
+
If needed, you can also add a packages.txt file at the root of the repository to specify Debian dependencies.
|
| 57 |
+
|
| 58 |
+
The gradio package is pre-installed and its version is set in the sdk_version field in the README.md file.
|
| 59 |
+
|
| 60 |
+
Personalize your Space
|
| 61 |
+
|
| 62 |
+
Make your Space stand out by customizing its emoji, colors, and description by editing metadata in its README.md file.
|
| 63 |
+
|
| 64 |
+
Documentation
|
| 65 |
+
|
| 66 |
+
Read the full documentation for gradio Spaces here.
|
| 67 |
+
|
requirements.txt
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Hugging Face Spaces requirements for Genie TTS
|
| 2 |
+
|
| 3 |
+
# Core dependencies
|
| 4 |
+
gradio>=4.0.0
|
| 5 |
+
torch>=2.0.0
|
| 6 |
+
torchaudio>=2.0.0
|
| 7 |
+
|
| 8 |
+
# Genie TTS package
|
| 9 |
+
genie-tts
|
| 10 |
+
|
| 11 |
+
# Audio processing
|
| 12 |
+
librosa>=0.10.0
|
| 13 |
+
soundfile>=0.12.0
|
| 14 |
+
scipy>=1.9.0
|
| 15 |
+
|
| 16 |
+
# ONNX Runtime for model inference
|
| 17 |
+
onnxruntime>=1.16.0
|
| 18 |
+
|
| 19 |
+
# Additional dependencies
|
| 20 |
+
numpy>=1.21.0
|
| 21 |
+
pandas>=1.5.0
|
| 22 |
+
Pillow>=9.0.0
|
| 23 |
+
|
| 24 |
+
# Hugging Face integrations
|
| 25 |
+
huggingface-hub>=0.17.0
|
| 26 |
+
transformers>=4.25.0
|
| 27 |
+
|
| 28 |
+
# Japanese text processing (for pyopenjtalk if needed)
|
| 29 |
+
# Note: pyopenjtalk might need system dependencies on some platforms
|
| 30 |
+
# pyopenjtalk # Uncomment if needed
|
| 31 |
+
|
| 32 |
+
# System utilities
|
| 33 |
+
psutil>=5.8.0
|
| 34 |
+
requests>=2.25.0
|
| 35 |
+
|
| 36 |
+
# Logging and monitoring
|
| 37 |
+
rich>=12.0.0
|
| 38 |
+
|
| 39 |
+
# File handling
|
| 40 |
+
pathlib2>=2.3.0
|