README.md

metadata

title: Multi Document Summarizer
emoji: 🔥
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 5.25.2
app_file: app.py
pinned: false
license: mit
short_description: Summarizes multiple docs (docx, pdf, etc.) with NLP & visual

Multi Document Summarization

This project provides a multi-document summarization tool using state-of-the-art NLP models like BART and Longformer. It supports various file formats and generates summaries along with visualizations like dendrograms, t-SNE plots, TF-IDF plots, and word clouds.

Features

• Summarizes multiple documents into concise summaries.
• Supports file formats: .docx, .txt, .html, .pdf, .csv, .xlsx, .json, .xml, .ppt, .pptx.
• Visualizations: Dendrogram, t-SNE, TF-IDF, Word Cloud.

Installation

1. Clone the repository:

   git clone https://github.com/your-username/abstractive-text-summarization.git
   

2. Navigate to the project directory:

   cd abstractive-text-summarization
   

3. Install dependencies:

   pip install -r requirements.txt
   

Usage

1. Run the application:

   python major_project_main.py
   

2. Open the Gradio interface in your browser.
3. Upload files and click "Summarize" to generate summaries and visualizations.

License

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