Falcon-OCR is an open-source optical character recognition (OCR) model designed for extracting text from images. It supports deployment via Docker and Python libraries, and is suitable for developers and ML engineers needing robust OCR capabilities. The model is MIT licensed and provides benchmarked performance.
Falcon OCR sits in PulseGate's Multimodal & vision category. It focuses on extracting text from images using an open-source, high-accuracy OCR model. It is built as an open-source project for machine learning engineers and developers. Falcon OCR is open source under the Apache-2.0 license. Falcon OCR is available on the web, the command line, and API, and it can be self-hosted.
tiiuae builds and maintains Falcon OCR, and it first shipped in 2026. Development happens publicly on GitHub with 726 stars and 13 commits in the last 90 days. Among its 5 catalogued features are OCR extraction, image-to-text, and docker support.
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