Pinned Loading

1. datalab-to/marker datalab-to/marker Public

   Convert PDF to markdown + JSON quickly with high accuracy

   Python 29.6k 2k

2. datalab-to/surya datalab-to/surya Public

   OCR, layout analysis, reading order, table recognition in 90+ languages

   Python 18.8k 1.3k

3. zero_to_gpt zero_to_gpt Public

   Go from no deep learning knowledge to implementing GPT.

   Jupyter Notebook 1.3k 219

4. datalab-to/chandra datalab-to/chandra Public

   OCR model that handles complex tables, forms, handwriting with full layout.

   Python 1.2k 109

5. datalab-to/pdftext datalab-to/pdftext Public

   Extract structured text from pdfs quickly

   Python 619 60

6. texify texify Public archive

   Math OCR model that outputs LaTeX and markdown

   Python 1.1k 89