Save memory when pruning MoE

• Prune MoE experts before loading model
• Unpin torch version from 2.2.2

Fix issue with torch and dependencies

Merge pull request #96 from VikParuchuri/dev

Fix publishing issue

Add OCR batch size option

Merge pull request #95 from VikParuchuri/dev

Add batch size to OCR

Set batch sizes programatically

• Programmatic batch sizes for all models
• Update package versions
• Bugfixes

Release ordering model

• Release reading order model
• Add Google Cloud OCR benchmarks to README

Release layout model

• Add layout model
• Multiprocessing for detection postprocessing (can be much faster)
• Fix minor bugs

Fix dependency import

Merge pull request #52 from VikParuchuri/dev

Fix import issue

Improve line detector

• Improved line detector with better recall and higher resolution
• Confidence scores for detection and recognition
• Beta layout detection model

Basic sorting, repetition detection, UTF-8 output

• Output JSON as UTF-8 so text can be scanned easily
• Improve output schema to include more information and be easier to parse
• Sort text lines in basic order, which will work in many cases
• Detect repetitions and truncate

v0.2.1: Merge pull request #18 from VikParuchuri/dev

• Fix bug with downloading render fonts for OCR