Typhoon-OCR-3B is a small multimodal model designed specifically for high-performance optical character recognition across various languages and document types. It accepts image inputs and outputs extracted text. It is available on Hugging Face for integration into document processing pipelines.
In the Foundation models & chat space, Typhoon Ocr 3b takes a focused approach. It focuses on extracting text accurately from images and documents using a compact open model. It is built as an open-source project for developers. Typhoon Ocr 3b is open source under the Apache-2.0 license. Typhoon Ocr 3b is available on the web, the command line, and API.
Behind Typhoon Ocr 3b is typhoon-ai, and the product first shipped in 2025. Development happens publicly on GitHub with 134 stars. Key capabilities include OCR, multimodal, and Vision Language Model.
Latest indexed changes and source events
typhoon-ai/typhoon-ocr-3b verified by the PulseGate indexer
Other apps tracked under the same category.
