Tonic's GOT OCR is a Hugging Face Space that lets users upload images and extract text using the GOT model. It supports multiple output modes including plain text, formatted HTML, and targeted extraction by bounding box or color. The interactive demo allows testing different extraction strategies on various image types. It is designed for developers and researchers working with document understanding and optical character recognition.
Tonic's GOT OCR is a Computer vision, OCR & document AI project. It focuses on converting text in images into structured, selectable, or formatted digital text. It is built as an open-source project for developers and researchers. Tonic's GOT OCR costs nothing to use. It runs on the web, the command line, and embeddable surfaces.
It is developed by Tonic. Among its 4 catalogued features are Image Upload, Plain Text Extraction, and HTML Output.
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