VHumanize

VHumanize is a web-based tool for transforming AI-generated text into natural, human-like content and detecting AI-generated text. It provides advanced paraphrasing, rewriting, and AI detection features, leveraging state-of-the-art NLP models and a modern Svelte frontend.

• 🔍 AI Detection: Detects AI-generated content at line and sentence levels, with visual highlighting and detailed statistics
• 🔄 Humanization Pipeline: Two-step process (Paraphrasing + Rewriting) to convert AI text into more human-like writing
• 🤖 Multi-Model Support: Choose from multiple transformer-based models (T5, BART, Pegasus, etc.) for paraphrasing and rewriting
• ⚡ Enhanced Mode: Optionally use advanced prompts and NLP techniques for higher-quality rewriting
• 🔬 Combined Humanize & Verify: Instantly humanize text and check for AI traces in a single workflow
• 📋 Copy & Share: Easily copy results to clipboard
• 📱 Responsive UI: Clean, modern interface built with SvelteKit and Vite

• Python 3.11+
• Flask - Web framework
• NLTK, spaCy, TextBlob - NLP processing and advanced rewriting
• Transformers (HuggingFace) - Paraphrasing and rewriting models (T5, BART, Pegasus)

• SvelteKit - Modern, component-based UI framework
• Vite - Fast build tool and dev server
• Svelte Stores - Reactive state management
• Lucide Icons - UI icons

humanizer/
├── detector.py # AI detection backend logic
├── download_models.py # Script to download required models
├── main.py # Backend server entry point
├── paraphraser.py # Paraphrasing logic and model management
├── rewriter.py # Advanced rewriting and NLP enhancements
├── requirements.txt # Python dependencies
├── README.md
├── frontend/
│ ├── package.json
│ ├── vite.config.js
│ ├── svelte.config.js
│ ├── src/
│ │ ├── app.html
│ │ ├── lib/
│ │ │ ├── script.js # Frontend logic and API calls
│ │ │ └── style.css # Main CSS
│ │ └── routes/
│ │ └── +page.svelte # Main Svelte page
│ └── static/
│ └── favicon.png
└── __pycache__/

• Python 3.11+
• Node.js 16+
• Git

1. Clone the repository

   git clone https://github.com/vardhin/vhumanize.git
   cd vhumanize

2. Backend Setup

   # Install Python dependencies
   pip install -r requirements.txt
   # Download required models
   python download_models.py
   # Start the backend server
   python main.py

   The API server will start at http://localhost:8080

3. Frontend Setup

   # Navigate to frontend directory
   cd frontend
   # Install Node.js dependencies
   npm install
   # Start the development server
   npm run dev

   The frontend will be available at http://localhost:5173

• Model Selection: Choose or recommend models for paraphrasing/humanization
• Enhanced Mode: Toggle for higher-quality, slower rewriting
• Detection Threshold: Adjust sensitivity for AI detection

Contributions are welcome! Please feel free to submit a Pull Request.

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

This project is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).

You are free to:

• Share — copy and redistribute the material in any medium or format
• Adapt — remix, transform, and build upon the material

Under the following terms:

• Attribution — You must give appropriate credit to Vardhin, provide a link to the license, and indicate if changes were made
• NonCommercial — You may not use the material for commercial purposes

See the LICENSE file for details or visit Creative Commons for more information.

• Built with SvelteKit and HuggingFace Transformers
• Icons by Lucide
• Thanks to all contributors and the open-source community

If you encounter any issues or have questions, please open an issue on GitHub.