metadata

title: AI Text Humanizer & Detector Pro
emoji: 🤖➡️👨
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: mit
short_description: Transform AI text to natural, human-like writing
tags:
  - text-processing
  - ai-detection
  - humanization
  - nlp
  - gradio

🤖➡️👨 AI Text Humanizer

🎯 Transform robotic AI text into natural, human-like writing

🚀 Quick Start • 📖 Documentation • 🔧 Features • 💡 Examples • 🤝 Contributing

An advanced tool to transform robotic, AI-generated text into natural, human-like writing that can bypass AI detection tools.

🚀 Features

🎯 Core Capabilities

🤖 Multiple AI Models: T5 & Pegasus paraphrasing
📝 Advanced Techniques: Vocabulary diversification
🔄 Batch Processing: Handle multiple texts/files
🎓 Academic Focus: Preserves professional tone
🛡️ Undetectable Output: Bypasses AI detection
🖥️ Multiple Interfaces: Simple, advanced & batch versions

⚡ Performance Features

🚀 Fast Processing: Optimized algorithms
💾 Memory Efficient: Smart chunking system
🔧 Error Handling: Graceful fallbacks
📊 Quality Control: Maintains meaning integrity
🌐 Web Interface: User-friendly Gradio UI
📱 Responsive Design: Works on all devices

📁 Project Structure

📦 AI Text Humanizer
├── 🎯 humanizer_app.py      # Advanced multi-model version
├── 🔧 humanizer_simple.py   # Reliable single-model version  
├── 📊 humanizer_batch.py    # Batch processing for files
├── 📋 requirements.txt      # Dependencies list
├── 🚀 app.py               # Deployment-ready version
└── 📖 README.md            # This documentation

File	Purpose	Best For
🎯 `humanizer_app.py`	Advanced features with AI detection	Maximum customization
🔧 `humanizer_simple.py`	Single T5 model, reliable	Quick & stable results
📊 `humanizer_batch.py`	Process multiple files	Bulk text processing
🚀 `app.py`	Web deployment version	Online hosting

🛠️ Installation

📋 Prerequisites

Python 3.8 or higher
4GB+ RAM recommended
2GB+ free space for models

🚀 Quick Setup

# 📥 Clone the repository
git clone https://github.com/SidddhantJain/Humaniser-Sid.git
cd Humaniser-Sid

# 🐍 Create virtual environment
python -m venv .venv

# ⚡ Activate environment
.venv\Scripts\activate  # Windows
source .venv/bin/activate  # Linux/Mac

# 📦 Install dependencies
pip install -r requirements.txt

# 🚀 Launch application
python humanizer_app.py

🔗 Alternative Installation

🎯 Advanced Version

python humanizer_app.py

✅ Full features
✅ AI detection
✅ Multiple models

🔧 Simple Version

python humanizer_simple.py

✅ Single model
✅ Fast & reliable
✅ Lightweight

📊 Batch Version

python humanizer_batch.py

✅ File processing
✅ CSV support
✅ Bulk operations

🎯 Usage

🖥️ Web Interface

🚀 Launch: Run any Python file
🌐 Access: Open browser to http://127.0.0.1:7860
📝 Input: Paste your AI-generated text
⚙️ Configure: Select humanization level
✨ Transform: Click "Humanize" for natural output

🎛️ Humanization Levels

Level	Icon	Description	Use Case
Light	🟢	Basic paraphrasing	Quick touch-ups
Medium	🟡	Paraphrasing + vocabulary + connectors	Balanced improvement
Heavy	🔴	All techniques + structure changes	Maximum humanization

📊 Batch Processing Features

📄 Text Files (.txt)

📝 Processes paragraph by paragraph
🔄 Maintains formatting
💾 Saves processed versions
⚡ Handles large documents

📈 CSV Files (.csv)

📊 Adds 'humanized' column
🔧 Preserves original data
📋 Batch processes multiple rows
📤 Exports enhanced datasets

🔧 How It Works

🧠 Advanced Techniques Pipeline

graph LR
    A[🤖 AI Text Input] --> B[📝 Multi-Model Paraphrasing]
    B --> C[📚 Vocabulary Diversification]
    C --> D[🔄 Sentence Structure Variation]
    D --> E[🔗 Academic Connector Integration]
    E --> F[🎯 Hedging Language Addition]
    F --> G[✂️ Smart Chunking]
    G --> H[👨 Human-like Output]

🎯 Core Algorithms

🔄 Multi-Model Paraphrasing: Avoids single-model patterns
📖 Vocabulary Diversification: Contextual synonym replacement
🏗️ Sentence Structure Variation: Natural flow modification
🔗 Academic Connector Integration: Professional transitions
🎭 Hedging Language: Academic tone preservation
✂️ Smart Chunking: Optimal text processing

🤖 AI Models Stack

Primary Model
Secondary Model
Synonym Engine
Flow Optimization

📊 Example Transformations

🤖 Input (AI-generated)

The implementation of machine learning algorithms 
in data processing systems demonstrates significant 
improvements in efficiency and accuracy metrics 
across various benchmark datasets.

📈 AI Detection Score: 85% (Very High)

👨 Output (Humanized)

Implementing machine learning algorithms within 
data processing frameworks shows notable 
enhancements in both efficiency and accuracy 
measures when evaluated across different 
benchmark datasets. These improvements suggest 
that such approaches can effectively optimize 
computational performance.