This Flask application utilizes the Pegasus Transformer model by Google for conditional text summarization. It allows users to input large text and receive a concise summary, making it ideal for processing articles, reports, or any long-form text data.

• Text Summarization: Uses the PegasusForConditionalGeneration model to generate a summary for the input text.
• CUDA Optimization: Leverages CUDA if available, allowing for faster summarization on GPU devices.
• Responsive Web Interface: The application provides a user-friendly interface with index.html for input and output.html to display results.

• Input: The user submits text via a form on the home page.
• Text Tokenization: The input text is tokenized and encoded for the Pegasus model.
• Summarization: The model generates a summary with specified minimum and maximum length constraints.
• Output: The summary is decoded and displayed on the output page.

• Python >= 3.10
• Flask
• Transformers
• gunicorn
• sentencepiece
• torch

1. Clone the repository

   git clone https://github.com/letsdoitbycode/Text-Summarization-Webapp.git
   cd Text-Summarization-Webapp

2. Create a virtual environment and activate it:

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install the required packages:

   pip install flask transformers torch sentencepiece gunicorn
   pip install requirements.txt   #else you can do this directly

4. Run the Flask app:

   python app.py

Text-Summarization-Webapp/
│
├── templates/
│   └── index.html          # HTML file for text input
│   └── output.html         # Output file for a output of summarisation
├── venv                    # Virtual environment
├── README.md               # This README file
├── app.py                  # Main Flask application
└── requirements.txt        # requirement file

Contributions are welcome! Please open an issue or submit a pull request for any changes or improvements.