Shypd.aiThe largest open index of AI toolsdeepdoctection is a Python library for document AI that orchestrates document layout analysis, OCR, and document/token classification. It supports PyTorch and integrates with various models from the Huggingface Hub.
Trending
About
deepdoctection is a comprehensive Python library designed for document understanding, offering robust capabilities in document layout analysis, optical character recognition (OCR), and document/token classification. It leverages PyTorch for all deep learning models and supports a wide array of fine-tuned models from the Huggingface Hub, including Bert, RobertA, LayoutLM, and LiLT. The library is modular, decomposed into sub-packages like dd-core, dd-datasets, and deepdoctection, allowing for flexible integration. Users can build and run custom document extraction pipelines, fine-tune pre-trained models, and seamlessly use them for inference. It also features text mining for native PDFs, language detection, and image deskewing/rotation.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
