Jupyter notebooks testing different OCR models for document parsing (Dolphin, MonkeyOCR, Marker, Nanonets, ...)
-
Updated
Aug 2, 2026 - Jupyter Notebook
#
document-parsing
Here are 3 public repositories matching this topic...
collection of notebooks for finetuning donut model for various visual document understanding tasks, using huggingface Trainer.
information-extraction donut document-processing visual-question-answering document-understanding document-parsing huggingface-tutorial
-
Updated
Oct 15, 2025 - Jupyter Notebook
Free, open-source Google Colab notebook that converts PDF & image files (JPG, PNG, BMP, TIFF, WEBP) into clean Markdown using Baidu's Unlimited-OCR (MIT license, 93%+ OmniDocBench). No API key, no cost — runs on free Colab GPU. PDF to Markdown, OCR, document parsing, image to text converter.
markdown ocr deep-learning transformers pytorch pdf-to-text image-to-text google-colab colab-notebook huggingface document-ai document-parsing ai-ocr pdf-to-markdown free-ocr deepseek-ocr unlimited-ocr open-source-ocr pdf-converter-toolkit
-
Updated
Aug 13, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the document-parsing topic, visit your repo's landing page and select "manage topics."