datalab-to/marker v1.8.3

New OCR model; better OCR heuristics

on GitHub

• New OCR model that is better all-around, but particularly at math
• Improved OCR heuristics, will now prioritize accuracy over speed
• Drop format_lines, since force_ocr is generally a bit more accurate, and less error-prone

What's Changed

• feat: allow option to keep tables split across pages by @zanussbaum in #813
• New OCR Model by @tarun-menta in #820
• Bump surya version by @VikParuchuri in #821

Full Changelog: v1.8.2...v1.8.3