Quipo-Oscar Donut Transformer

This project demonstrates how to process PDF files by splitting them into pages, extracting data using a transformer model (Donut Transformer), and saving the extracted data as JSON files in the same directory as the original PDFs.

Features

• Split PDF files into individual pages (PNG images).
• Extract data from each page using a transformer model (e.g., Donut Transformer).
• Save extracted data in JSON format alongside the original PDF files.

Installation

1. Clone the repository:

git clone https://github.com/Adarsh-aot/quipo-oscar.git

cd quipo-oscar

Install the required Python packages:

pip install -r requirements.txt

Run code

python main.py

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

• Project Overview: The README provides an overview of the project, explaining its purpose and key features related to PDF processing and data extraction using a transformer model.

• Installation: Instructions for cloning the repository and installing the required Python packages using pip.

• Usage: Detailed instructions on how to run the main.py script to process PDF files and convert them into JSON format. It includes information about input/output directories and running the script.

• Configuration: Guidance on customizing configuration settings (e.g., model parameters, output directories)

• Requirements: List of software requirements and dependencies needed to run the project, including Python version and Donut Transformer model.

• Directory Structure: Description of the directory structure used in the project, including directories for input PDF files, output PNG images, output JSON files, and main script files.

• Contributing: Encouragement for contributions from the community, with instructions on how to submit issues or pull requests on GitHub.

• License: Information about the project's license (in this case, the MIT License) for users and contributors.