OnnxTR and doctr

OnnxTR is a wrapper around docTR that converts its models to ONNX format for optimized inference, making them ecosystem siblings where one provides the core library and the other provides a runtime-specific implementation.

OnnxTR
60
Established
doctr
59
Established
Maintenance 10/25
Adoption 11/25
Maturity 25/25
Community 14/25
Maintenance 13/25
Adoption 10/25
Maturity 16/25
Community 20/25
Stars: 176
Forks: 18
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 5,956
Forks: 627
Downloads:
Commits (30d): 1
Language: Python
License: Apache-2.0
No risk flags
No Package No Dependents

About OnnxTR

felixdittrich92/OnnxTR

OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless, high-performing & accessible OCR

This tool helps you convert scanned documents, images, or even web pages into editable and searchable text. You provide documents in formats like PDF or JPG, and it gives you back the extracted text, intelligently grouped into words and lines. It's designed for anyone who needs to quickly and accurately get text out of various document types.

document-processing data-entry information-extraction digital-archiving text-digitization

About doctr

mindee/doctr

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

This project helps anyone who needs to extract text from documents like PDFs, images, or even webpages. It takes your document files as input and outputs the identified text, including its location on the page. You can use it to convert scanned documents into searchable and editable text.

document-processing data-extraction digitization information-retrieval text-recognition

Scores updated daily from GitHub, PyPI, and npm data. How scores work