General OCR Theory (GOT) 2.0 is an open model that unifies various OCR tasks including scene text, document parsing, and formula recognition into a single end-to-end vision-language model. Hosted on Hugging Face, it supports multilingual OCR and can be used with the Transformers library.
GOT OCR 2.0 Hf is a Multimodal & vision project. It focuses on extracting structured text and understanding complex document layouts from images at high accuracy. GOT OCR 2.0 Hf is an open-source project aimed at developers. GOT OCR 2.0 Hf is open source under the Open Source license. It ships for the web, the command line, and API.
Behind GOT OCR 2.0 Hf is StepFun, based in China, and it first shipped in 2024. The project is developed in the open on GitHub with 8.2k stars. Among its 3 catalogued features are OCR, Document Understanding, and multilingual.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do