Extract text from documents and images with Datalab Marker and OCR

This post introduces the integration of Datalab Marker and OCR models on Replicate. It details the capabilities of Marker for parsing various document formats into markdown or JSON, including handling tables, math, and code, and supporting structured field extraction via JSON Schema. It also describes the OCR model's ability to detect text in 90 languages from images and documents, providing reading order and table grids. Performance benchmarks are presented, showing Marker outperforming established tools like Tesseract and GPT-4o on the olmOCR-Bench dataset. Pricing for both models is also detailed.