qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-10-30 02:34:13 +01:00
Code Issues Projects Releases Wiki Activity

✨ Add GT4HistOCR model download for Calamari 1.x

Browse source
This commit is contained in:
Gerber, Mike 2020-11-19 17:27:31 +01:00
parent db1de930a3
commit a3ae0a325d
2 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
Dockerfile-ocrd_tesserocr
View file

@ -24,7 +24,7 @@ COPY data/tesseract-models/GT4HistOCR/GT4HistOCR_2000000.traineddata $TESSDATA_P
# Build pip installable stuff
RUN ${PIP_INSTALL} \
# Now the real stuff:
'ocrd_tesserocr >= 0.9.0'
'ocrd_tesserocr >= 0.9.5'
# Check pip dependencies

2
build
View file

@ -15,7 +15,7 @@ get_from_annex() {
}
get_from_web() {
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/model.tar.xz' 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200'
# XXX Calamari 1 model
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/model.tar.xz' 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100'
download_to 'https://qurator-data.de/tesseract-models/GT4HistOCR/models.tar' 'tesseract-models/GT4HistOCR'
download_to 'https://qurator-data.de/sbb_textline_detector/models.tar.gz' 'textline_detection'
download_to --strip-components 1 'https://qurator-data.de/sbb_binarization/models.tar.gz' 'sbb_binarization'