Book Translator

Book Translator is a powerful application for translating books and large text documents (.txt files) between multiple languages using a two-stage translation process: Google Translate for initial translation and Ollama AI models for literary refinement. It works with plain text format only and combines a Flask backend with a React frontend to provide a smooth and efficient translation experience.

Key Features

• 🔄 Two-stage translation process:
  • Stage 1: Fast initial translation using Google Translate
  • Stage 2: Literary refinement using Ollama AI models
• 🌍 Support for multiple languages including English, Russian, German, French, Spanish, Italian, Chinese, and Japanese
• 🤖 Integration with Ollama AI models for high-quality refinements
• 🚀 Real-time translation progress tracking for both stages
• 📚 Translation history and status monitoring
• 💾 Efficient caching system for improved performance
• 🔄 Automatic error recovery and retry mechanisms
• 📊 Real-time metrics and system monitoring
• 📱 Modern, responsive UI with React and Tailwind CSS

Demo

Experience the translation process in modern, user-friendly interface:

Translation Process

The application uses a sophisticated two-stage translation approach:

Stage 1: Initial Translation

• Uses Google Translate API for fast initial translation
• Handles large volumes of text efficiently
• Provides basic translation quality
• Progress tracking for initial translation stage

Stage 2: Literary Refinement

• Uses Ollama AI models to refine the initial translation
• Improves literary quality and natural language flow
• Maintains context and style
• Separate progress tracking for refinement stage

Prerequisites

• Python 3.7+
• Ollama installed and running
• Node.js (for development)

Quick Start

1. Clone the repository

git clone https://github.com/kazkozdev/book-translator.git
cd book-translator

2. Install dependencies

pip install -r requirements.txt

3. Pull required Ollama model

ollama pull gemma2:27b

4. Start the application

python translator.py

5. Access the application

• Open http://localhost:5001 in your browser

Architecture

book-translator/
├── translator.py        # Flask backend
├── static/             # Frontend files
├── uploads/            # Temporary uploads
├── translations/       # Completed translations
├── logs/              # Application logs
├── translations.db     # Main database
└── cache.db           # Cache database

API Reference

Translation Endpoints

• POST /translate - Start translation process (both stages)
• GET /translations - Get history
• GET /translations/<id> - Get translation details including stage progress
• GET /download/<id> - Download refined translation
• POST /retry-translation/<id> - Retry failed translation

System Endpoints

• GET /models - List available Ollama models
• GET /metrics - System metrics
• GET /health - Service health check
• GET /failed-translations - List failed translations

Contributing

We welcome contributions! Here's how:

1. Fork the repository
2. Create feature branch (git checkout -b feature/AmazingFeature)
3. Commit changes (git commit -m 'Add AmazingFeature')
4. Push to branch (git push origin feature/AmazingFeature)
5. Open Pull Request

License

MIT License - see LICENSE file

---

Made with ❤️
⭐ Star us on GitHub!