historical-ocr / structured_ocr.py

Commit History

modularize + nest scripts; reduce technical debt
94e74f0

milwright commited on

Fix structured_ocr.py syntax errors
deb9332

milwright commited on

Consolidate segmentation improvements and code cleanup
42dc069

milwright commited on

Rolling out modular v2
c04ffe5

milwright commited on

Integrate image segmentation and language detection modules
836388f

milwright commited on

Improve language detection with mistral-ocr-latest model
aabc02c

milwright commited on

Update app.py, structured_ocr.py, and UI layout
8d3bfba

milwright commited on

enhanced OCR functionality and efficiency, simplified preprompting, etc
75ead00

milwright commited on

Restore working Language enum implementation
6931bb0

milwright commited on

Fix Language enum duplicate key error - prevent duplicating keys in LanguageMeta class
4edf687

milwright commited on

Add robust dependency handling with fallbacks for missing packages
e65ba1a

milwright commited on

Fix f-string backslash escape syntax error
341cb11

milwright commited on

Fix syntax error and responsive layout issues
3bdacb6

milwright commited on

Fix document metadata white bar issue and JSON parsing error
2a692ed

milwright commited on

Update Historical OCR with specified input files
59aaeae

milwright commited on