The Donut model is a state-of-the-art deep learning model developed by Naver AI Lab for document understanding tasks. It combines computer vision and natural language processing techniques to extract structured information from unstructured documents such as receipts, invoices, and forms. The model is fine-tuned for receipt processing tasks and achieves high accuracy in recognizing text and extracting relevant information.
Dependencies
- Python 3.x
- FastAPI
- PyTorch
- Transformers
- PIL (Python Imaging Library)
About the Donut Model
The Donut model is a state-of-the-art deep learning model developed by Naver AI Lab for document understanding tasks. It combines computer vision and natural language processing techniques to extract structured information from unstructured documents such as receipts, invoices, and forms. The model is fine-tuned for receipt processing tasks and achieves high accuracy in recognizing text and extracting relevant information.
Github: https://github.com/muslimalfatih/scan-bill
Demo: https://cln.sh/04Q6gqrT