108 lines
3.2 KiB
Markdown
108 lines
3.2 KiB
Markdown
# Clean-Tracks - Audio Censorship System
|
|
|
|
An intelligent audio processing tool that automatically detects and censors explicit content in audio files, featuring both a user-friendly web interface and powerful command-line tools.
|
|
|
|
## 🎯 Overview
|
|
|
|
Clean-Tracks uses advanced speech recognition (OpenAI Whisper) to detect and remove explicit words from audio files while preserving audio quality. Perfect for content creators, educators, and parents who need to make audio content appropriate for all audiences.
|
|
|
|
## ✨ Features
|
|
|
|
- **🎵 Multi-Format Support**: Process MP3, WAV, FLAC, M4A, OGG, and more
|
|
- **🤖 AI-Powered Detection**: Uses Whisper for accurate speech recognition
|
|
- **🎨 Web Interface**: Intuitive drag-and-drop interface with real-time progress
|
|
- **⚡ Command Line**: Powerful CLI for batch processing and automation
|
|
- **📝 Customizable Word Lists**: Manage your own explicit word lists with severity levels
|
|
- **🔊 Multiple Censorship Styles**: Choose between silence, beep, or white noise
|
|
- **📊 Visual Feedback**: See waveforms with detected words highlighted
|
|
- **🚀 Batch Processing**: Process multiple files simultaneously
|
|
- **📱 Mobile Responsive**: Works on desktop, tablet, and mobile devices
|
|
|
|
## 🚀 Quick Start
|
|
|
|
### Installation
|
|
|
|
```bash
|
|
# Clone the repository
|
|
git clone https://github.com/yourusername/clean-tracks.git
|
|
cd clean-tracks
|
|
|
|
# Create virtual environment
|
|
python3 -m venv venv
|
|
source venv/bin/activate # On Windows: venv\Scripts\activate
|
|
|
|
# Install dependencies
|
|
pip install -r requirements.txt
|
|
|
|
# Run setup
|
|
python setup.py install
|
|
```
|
|
|
|
### Web Interface
|
|
|
|
```bash
|
|
# Start the web server
|
|
python -m clean_tracks.web
|
|
|
|
# Open browser to http://localhost:5000
|
|
```
|
|
|
|
### Command Line
|
|
|
|
```bash
|
|
# Process a single file
|
|
clean-tracks process audio.mp3 --output clean_audio.mp3
|
|
|
|
# Batch process files
|
|
clean-tracks batch *.mp3 --output-dir cleaned/
|
|
|
|
# Manage word lists
|
|
clean-tracks words add "example" --severity high
|
|
clean-tracks words list
|
|
clean-tracks words export my_words.csv
|
|
```
|
|
|
|
## 📋 Requirements
|
|
|
|
- Python 3.11+
|
|
- FFmpeg (for audio processing)
|
|
- 4GB RAM minimum (8GB recommended for large files)
|
|
- GPU optional but recommended for faster processing
|
|
|
|
## 🛠️ Technology Stack
|
|
|
|
- **Backend**: Python, Flask, OpenAI Whisper
|
|
- **Audio Processing**: PyDub, Librosa, FFmpeg
|
|
- **Frontend**: HTML5, Bootstrap 5, JavaScript
|
|
- **Real-time**: WebSocket (Socket.io)
|
|
- **Database**: SQLite
|
|
- **Testing**: Pytest, Playwright
|
|
|
|
## 📖 Documentation
|
|
|
|
- [User Guide](docs/user-guide.md)
|
|
- [API Documentation](docs/api.md)
|
|
- [Development Guide](docs/development.md)
|
|
- [Word List Management](docs/word-lists.md)
|
|
|
|
## 🤝 Contributing
|
|
|
|
We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
|
|
|
|
## 📄 License
|
|
|
|
This project is licensed under the MIT License - see [LICENSE](LICENSE) file for details.
|
|
|
|
## 🙏 Acknowledgments
|
|
|
|
- Built on top of OpenAI's Whisper for speech recognition
|
|
- Uses components adapted from the Personal AI Assistant project
|
|
- Inspired by the need for family-friendly content creation tools
|
|
|
|
## 📧 Support
|
|
|
|
For issues, questions, or suggestions, please open an issue on GitHub or contact the maintainers.
|
|
|
|
---
|
|
|
|
**Note**: This project is in active development. Features and API may change. |