Multilingual Text Summarizer

📝 Multilingual Text Summarizer is a web application that summarizes text, PDFs, and images in multiple languages using a T5 transformer model. The application is built with Streamlit, EasyOCR, and Hugging Face Transformers.

Features

• Summarize text input directly
• Summarize content from uploaded PDF, TXT, and image files
• Detect and handle multiple languages
• Translate summarized text to English
• Chat-like prompt system for refining summaries

Demo

You can try the live demo on Streamlit Cloud.

Screenshots

Installation

Local Setup

1. Clone the repository:

   git clone https://github.com/RobinMillford/llm-based-text-summarizer.git
   cd LLM-Based-Text-Summarizer

2. Create and activate a virtual environment:

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

3. Install dependencies:

   pip install -r requirements.txt

4. Run the Streamlit app:

   streamlit run app.py

Docker

1. Pull the Docker image:

   docker pull yamin69/summarizer:latest

2. Run the Docker container:

   docker run -p 8501:8501 yamin69/summarizer:latest

Usage

1. Navigate to the app URL.
2. Choose an input method:
   • Direct Text Input
   • Upload File (PDF, TXT, Image)
3. Enter or upload your content.
4. Optionally add prompts to refine the summary.
5. Click "Generate Summary" to get the summarized text.

Contributing

1. Fork the repository:

   git fork https://github.com/RobinMillford/llm-based-text-summarizer.git

2. Create a branch:

   git checkout -b feature-branch

3. Make your changes and commit them:

   git commit -am 'Add new feature'

4. Push to the branch:

   git push origin feature-branch

5. Create a new Pull Request.

License

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

Acknowledgments

• Streamlit
• Hugging Face
• EasyOCR

---

For any issues, please create a new issue.