v1.6.0

datalab-to/markerv1.6.0Feb 28, 2025by VikParuchuri

AI Summary

Expands support to Office formats (Word, PowerPoint, Excel), HTML, and EPub, alongside improved inline math detection.

Key Highlights

Added support for DOCX, PPTX, XLSX, HTML, and EPUB
Improved text detection model for better OCR
Improved inline math detection with new model
Added `--redo-inline-math` option for highest quality math detection
Support for Claude model

New Features

Multi-format support (DOCX, PPTX, XLSX, HTML, EPUB)
Improved text detection model
Improved inline math detection
Claude model support

Full Release Notes

## Support xlsx, docx, pptx, html, epub

Marker now has support for additional document formats.  You have to run `pip install marker-pdf[full]` to install all the dependencies.

## Improved text detection

OCR should now work better due to an improved text detection model.

## Inline math improvements

- Better inline math detection with an improved model.
- Inline math lines are now inference.
- `--redo-inline-math` option to enable the highest quality math detection

## Misc improvements

- Support for the claude model
- Improve benchmarking scripts
- Merge lines better with new text detection model

## What's Changed
* Inline math by @VikParuchuri in https://github.com/VikParuchuri/marker/pull/571
* Add Support for DOCX, PPTX, XLSX, HTML and Epub by @iammosespaulr in https://github.com/VikParuchuri/marker/pull/501
* Fix character encoding issues when loading JSON configuration files by @vicenciomf2 in https://github.com/VikParuchuri/marker/pull/574
* Dev by @VikParuchuri in https://github.com/VikParuchuri/marker/pull/573

## New Contributors
* @vicenciomf2 made their first contribution in https://github.com/VikParuchuri/marker/pull/574

**Full Changelog**: https://github.com/VikParuchuri/marker/compare/v1.5.5...v1.6.0