discover · compare · collections · requirements · contribute · feed · watching · stats · help with your tokens
clovaai/donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
History and source changes · Reports and owner responses · Compare
Similar
- datalab-to/chandra
OCR model that handles complex tables, forms, handwriting with full layout.
Why this match
topics ocr; license differs: MIT → Apache-2.0
- getomni-ai/zerox
OCR & Document Extraction using vision models
Why this match
topics ocr; language differs: Python → TypeScript
- pytorch/vision
Datasets, Transforms and Models specific to Computer Vision
Why this match
topics computer-vision; license differs: MIT → BSD-3-Clause
- Zipstack/unstract
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Why this match
topics document-ai, ocr; license differs: MIT → AGPL-3.0
- tesseract-ocr/tessdata
Trained models with fast variant of the "best" LSTM models + legacy models
Why this match
topics ocr; license differs: MIT → Apache-2.0
- NLP-LOVE/ML-NLP
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。
Why this match
topics nlp; language differs: Python → Jupyter Notebook
- crownpku/Awesome-Chinese-NLP
A curated list of resources for Chinese NLP 中文自然语言处理相关资料
Why this match
topics nlp; license differs: MIT → Apache-2.0
- microsoft/AI-For-Beginners
12 Weeks, 24 Lessons, AI for All!
Why this match
topics computer-vision, nlp; language differs: Python → Jupyter Notebook