OvisOCR2

OvisOCR2 is a compact 0.8B parameter end-to-end document-parsing model that transforms document page images into structured Markdown. By eliminating the need for complex multi-stage pipelines (layout detection, OCR, and reassembly), it provides a streamlined solution for extracting text, tables, formulas, and visual regions in natural reading order.

OvisOCR2 is a compact 0.8B parameter end-to-end document-parsing model that transforms document page images into structured Markdown. By eliminating the need for complex multi-stage pipelines (layout detection, OCR, and reassembly), it provides a streamlined solution for extracting text, tables, formulas, and visual regions in natural reading order.

• 01End-to-end document parsing in a single pass
• 02Outputs structured Markdown with HTML tables and LaTeX formulas
• 03Highly efficient 0.8B parameter size suitable for local and edge deployment
• 04State-of-the-art performance (96.58 on OmniDocBench v1.6)
• 05Full compatibility with vLLM, Transformers, and SGLang inference stacks