Typhoon-OCR-7B is an open-source 7 billion parameter multimodal model specialized for optical character recognition and document understanding tasks. It accepts both text and image inputs to extract structured information from scanned documents, screenshots, and complex layouts. Hosted on Hugging Face, it is designed for developers integrating high-accuracy OCR capabilities into applications via local inference or API endpoints.
In the Foundation models & chat space, Typhoon Ocr 7b takes a focused approach. It focuses on extracting structured text accurately from scanned documents and images at scale. Typhoon Ocr 7b is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API, and it can be self-hosted.
Typhoon AI builds and maintains Typhoon Ocr 7b, and the product first shipped in 2025. The project is developed in the open on GitHub with 136 stars. Among its 3 catalogued features are OCR Extraction, Multimodal Input, and Document Parsing. It exposes integrations via a public API.
Latest indexed changes and source events
typhoon-ai/typhoon-ocr-7b verified by the PulseGate indexer
Other apps tracked under the same category.
