Spaces:

milwright
/

historical-ocr

Running

App Files Files Community

Ctrl+K

Ctrl+K

1 contributor

History: 97 commits

milwright's picture

Update README.md

6a1f69b verified 9 months ago

__pycache__
Integrate image segmentation and language detection modules 11 months ago
input
Upload baldwin-15th-north.jpg 12 months ago
static
Update Historical OCR with specified input files 12 months ago
ui
add init for ui and utils/helpers 11 months ago
utils
fix cline 11 months ago
.DS_Store

8.2 kB
fix cline 11 months ago
.gitattributes

169 Bytes
Update Historical OCR with specified input files 12 months ago
.gitignore

645 Bytes
fix cline 11 months ago
README.md

1.9 kB
Update README.md 9 months ago
app.py

28.7 kB
modularize + nest scripts; reduce technical debt 11 months ago
config.py

3.66 kB
modularize + nest scripts; reduce technical debt 11 months ago
constants.py

14.3 kB
Rolling out modular v2 11 months ago
error_handler.py

2.75 kB
Reconcile main with preview-improvements branch, implementing modular structure, raw text editing, and enhanced framing 11 months ago
image_segmentation.py

11.5 kB
Fix OCR processing variable scope issue by using explicit module reference for apply_preprocessing_to_file 11 months ago
letterhead_handler.py

7.44 kB
Fix OCR processing variable scope issue by using explicit module reference for apply_preprocessing_to_file 11 months ago
ocr_processing.py

37.7 kB
modularize + nest scripts; reduce technical debt 11 months ago
ocr_utils.py

3.11 kB
Rolling out modular v2 11 months ago
packages.txt

28 Bytes
Update Historical OCR with specified input files 12 months ago
pdf_ocr.py

2.41 kB
Update Historical OCR with specified input files 12 months ago
preprocessing.py

26 kB
Rolling out modular v2 11 months ago
process_file.py

2.17 kB
Rolling out modular v2 11 months ago
requirements.txt

569 Bytes
modularize + nest scripts; reduce technical debt 11 months ago
structured_ocr.py

112 kB
modularize + nest scripts; reduce technical debt 11 months ago
ui_components.py

28.4 kB
Apply light preprocessing by default (grayscale, denoise, contrast=5) to improve OCR readability 11 months ago
utils.py

16.1 kB
Consolidate segmentation improvements and code cleanup 11 months ago