0
I Use This!
Inactive

Commits : Listings

Analyzed 1 day ago. based on code collected 2 days ago.
May 14, 2023 — May 14, 2024
Commit Message Contributor Files Modified Lines Added Lines Removed Code Location Date
make abbyy2hocr work in SGE More... over 11 years ago
include blank ocr_line element even when there are no words therein, in order to align better More... over 11 years ago
include more process information regarding federizing More... over 11 years ago
modify so that works with SGE More... over 11 years ago
add spellcheck and Greek/Latin combining More... over 11 years ago
make last parameter the output file, so as to work in SGE More... over 11 years ago
reformat and parallelize with python multiprocessing More... over 11 years ago
get all the words in body of TEI document More... over 11 years ago
remove old spell-check command More... over 11 years ago
change debug messages More... over 11 years ago
add script to make dictionary of form 'word,#FREQ' More... over 11 years ago
add script to apply edits in csv file to words in a given hocr document More... over 11 years ago
script to modify a Gamera classifier so that it removes a glyph whose name matches the input More... over 11 years ago
bash shell loop to combine Latin and Greek hocr files en masse More... over 11 years ago
script to convert colour .jp2s to nicely compressed gray pngs More... over 11 years ago
don't strip numbers from spell-checked words (they could be errors for letters) More... over 11 years ago
when submitting multiple books, make them wait for completion of the book before; and move sge script output More... over 11 years ago
turn off underdot- and macron- finding by default More... over 11 years ago
correct order of combining diacritics: breathing, then accent; and more aggressive semicolon finding More... over 11 years ago
token splitting strips and recombines numbers at end of word More... over 11 years ago
add split_text_token to greek_tools More... over 11 years ago
make spellcheck file from dictionary and text More... over 11 years ago
add routine to delete macrons below More... over 11 years ago
underdots now discovered More... over 11 years ago
Merge branch 'fixWanderingBreathMarks' More... over 11 years ago
remove duplicate classify call More... over 11 years ago
try to make sure combo combinings get put in the right place, too More... over 11 years ago
try location to discern initial breathing More... over 11 years ago
add debugging to munge More... over 11 years ago
avoid ImageSegmentationError More... over 11 years ago