GOT-OCR2.0
OCR model
A Python implementation of an end-to-end OCR model for unified general OCR theory, supporting various formats and fine-grained recognition.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
6k stars
53 watching
515 forks
Language: Python
last commit: 6 days ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 tesseract-ocr/tesseract | An OCR engine capable of recognizing text in images from various languages and formats. | 62,363 |
 jaidedai/easyocr | An OCR system that supports multiple languages and writing scripts. | 24,528 |
 ofa-sys/ofa | Develops a unified sequence-to-sequence learning framework to unify modalities and tasks through pretraining and fine-tuning | 2,419 |
 openiti/ocr_gs_data | Provides gold standard data for training and testing optical character recognition (OCR) engines. | 15 |
 chreul/ocr_testdata_earlyprintedbooks | Provides test data and models for training Optical Character Recognition (OCR) systems on historical printed books. | 10 |
 hrnet/hrnet-semantic-segmentation | An implementation of a high-resolution neural network architecture for semantic segmentation tasks. | 3,156 |
 ryanfb/ancientgreekocr-ocr-evaluation-tools | A collection of tools and scripts to evaluate the accuracy of Optical Character Recognition (OCR) systems | 22 |
 kwai-kolors/kolors | A Python framework for training and deploying photorealistic text-to-image synthesis models. | 3,862 |
 otiai10/gosseract | An OCR package using Tesseract C++ library to extract text from images | 2,718 |
 openarabic/ocr_gs_data | A collection of double-checked gold standard data for training and testing OCR engines. | 13 |
 scut-dlvclab/gpt-4v_ocr | Evaluates the Optical Character Recognition capabilities of GPT-4V(ision) using various tasks and scenarios to identify its strengths and weaknesses | 120 |
 emedvedev/attention-ocr | A TensorFlow model for recognizing text in images using visual attention and a sequence-to-sequence architecture. | 1,077 |
 ibm/max-ocr | An optical character recognition system deployed as a web service using a trained Tesseract OCR model | 47 |
 oeg-upm/gtfs-bench | Provides a benchmarking framework for evaluating declarative knowledge graph construction engines in the transport domain | 17 |
 ub-mannheim/ocr-fileformat | Tool for converting and validating OCR file formats | 180 |