Transform AI-generated text into authentic, human-like content that bypasses AI detection systems.

Python Ollama License GitHub Issues GitHub Stars Contributions Welcome

AI Humanizer is a powerful tool that transforms AI-generated text into natural, human-sounding content. Built on research findings about what bypasses AI detectors in 2025, it focuses on:

• Perplexity variation - Unpredictable word choices
• Burstiness - Mixing short and long sentences dramatically
• Human quirks - Contractions, filler words, incomplete thoughts
• Emotional authenticity - Personal voice and natural speech patterns

• 🎯 High Success Rate - Designed to achieve <10% AI detection scores
• 🔄 Batch Processing - Process entire CSV files efficiently
• 💾 Resume Support - Continue from where you left off if interrupted
• 🧪 Testing Scripts - Verify your setup before full runs
• 📊 Progress Tracking - Real-time progress bars with tqdm
• 🎨 Multiple Prompt Versions - Optimized prompts for different use cases

1. Python 3.8+ installed on your system
2. Ollama installed and running (Download here)
3. Llama3 model pulled in Ollama

# Install Ollama, then run:
ollama pull llama3:8b

1. Clone the repository:

git clone https://github.com/Mohit1053/Humanizer.git
cd Humanizer

2. Install dependencies:

pip install -r requirements.txt

3. Verify your setup:

python test_humanizer.py

1. Quick Test (5 samples)

   python test_humanizer.py

   Test the humanizer on 5 sample rows to verify everything works.

2. Generate Test Samples

   python generate_test_samples.py

   Creates formatted samples ready for AI detection testing.

3. Full CSV Processing

   python humanize_v2.py

   Process your entire CSV file with humanized text.

Edit the configuration section in any script:

# Input/Output
INPUT_CSV = "your_input_file.csv"
OUTPUT_CSV = "your_output_file.csv"
# Model Settings
MODEL = 'llama3:8b'
BATCH_SIZE = 50
# Processing
START_ROW = 0 # Resume from a specific row
DELAY_MIN = 0.5 # Rate limiting
DELAY_MAX = 1.0

Humanizer/
├── humanize_v2.py # Main humanizer script (optimized)
├── test_humanizer.py # Quick test script (5 samples)
├── generate_test_samples.py # Generate formatted test samples
├── generate_samples.py # Alternative sample generator
├── quick_test.py # Quick testing utilities
├── single_test.py # Test single text transformation
├── optimize_prompts.py # Prompt optimization experiments
├── humanize_csv.py # Legacy version
├── final_pledges_merged.csv # Sample input data
├── test_results.csv # Test output results
├── TEST_SAMPLES_READY.md # Pre-generated test samples
└── README.md # This file

After humanizing your text, test it at:

• GPTZero - Goal: <10% AI detection
• ZeroGPT - Goal: <10% AI detection

See TEST_SAMPLES_READY.md for pre-generated samples ready for testing.

The humanizer uses carefully crafted prompts that instruct the LLM to:

1. Preserve exact emotional meaning - Keep the core message intact
2. Add natural speech patterns - "honestly", "like", "you know", "I mean"
3. Use heavy contractions - I'm, can't, won't, it's, that's, don't
4. Mix sentence lengths - Very short (3-5 words) to long rambling ones
5. Sound conversational - Like venting to a close friend
6. Include self-doubt - Natural human uncertainty

Original (AI-generated):

Surgery prep is torture, thinking through every step as if it's my final test. Each incision, each stitch might mean life or death.

Humanized:

Honestly, prep for surgery is just brutal, you know? Like, I'm literally thinking through every single step like it's my final exam or something. Each incision, each stitch - I mean, what if I mess up and someone dies on the table?

• Processing Speed: ~50 rows per minute (with rate limiting)
• AI Detection Score: Typically 0-10% on GPTZero and ZeroGPT
• Batch Efficiency: Resume capability prevents data loss
• Model Used: Llama3 8B (free, runs locally)

# Check if Ollama is running
ollama list
# Start Ollama service if needed
ollama serve

# Pull the required model
ollama pull llama3:8b
# Verify installation
ollama list

• Check CSV file path is correct
• Ensure the pledge column name matches your CSV
• Try testing with test_humanizer.py first

Contributions are welcome! Feel free to:

• Report bugs
• Suggest new features
• Submit pull requests
• Share prompt improvements

We welcome contributions! Please see our Contributing Guidelines for details on:

• How to fork and set up the project
• Code style guidelines
• Commit message format
• Pull request process

See CHANGELOG.md for a detailed history of changes.

This project is licensed under the MIT License - see the LICENSE file for details.

This tool is for educational and research purposes. Always ensure your use case complies with relevant terms of service and ethical guidelines.

• Built with Ollama for local LLM inference
• Uses Meta's Llama3 model
• Research-based approach to AI detection bypassing

For questions or feedback, please open an issue on GitHub.

Made with ❤️ by Mohit1053