├── artifacts
    ├── pdf.png
    ├── nuogat.png
    └── nougat process.png
└── README.md


/artifacts/pdf.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/inuwamobarak/nougat/HEAD/artifacts/pdf.png


--------------------------------------------------------------------------------
/artifacts/nuogat.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/inuwamobarak/nougat/HEAD/artifacts/nuogat.png


--------------------------------------------------------------------------------
/artifacts/nougat process.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/inuwamobarak/nougat/HEAD/artifacts/nougat process.png


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Nougat: Revolutionizing OCR for Scientific Documents
 2 | 
 3 | ![nuogat](https://github.com/inuwamobarak/nougat/assets/65142149/bb997529-11c9-4e3e-baf4-f0d479936037)
 4 | 
 5 | ## About Nougat
 6 | 
 7 | Nougat is an advanced Transformer-based OCR model that simplifies the process of converting complex scientific documents, often stored in PDF format, into a common and machine-readable Markdown format. Developed by a team of experts, Nougat leverages state-of-the-art architecture and training techniques to make scientific knowledge more accessible and usable.
 8 | 
 9 | ## Key Features
10 | 
11 | - **Transformer Architecture:** Nougat uses a Swin Transformer as a vision encoder and an mBART-based text decoder, allowing for end-to-end transcription of scientific PDFs.
12 | 
13 | - **End-to-End Training:** With Nougat, there's no need for complex pipelines. The model takes raw pixels as input and generates Markdown text as output, simplifying the entire OCR process.
14 | 
15 | - **Bridging the Gap:** Nougat not only transcribes scientific documents but also bridges the gap between human-readable content and machine-readable text, making it easier to access and utilize scientific knowledge.
16 | 
17 |    ```bash
18 |    git clone https://github.com/inuwamobarak/nougat.git
19 | 


--------------------------------------------------------------------------------