qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-06-09 14:49:53 +02:00
Code Issues Projects Releases Wiki Activity

⚙️ Get tessdata_best from git-annex/our mirror to make downloads more robust

Browse source
This commit is contained in:
Gerber, Mike 2020-08-05 16:03:17 +02:00
parent 6ae31395a3
commit 72693071e0
2 changed files with 3 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
build
View file

@ -9,11 +9,13 @@ get_from_annex() {
annex_get 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200/*.ckpt*'
annex_get 'tesseract-models/GT4HistOCR/*.traineddata'
annex_get 'textline_detection/*.h5'
annex_get 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz'
}
get_from_web() {
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/model.tar.xz' 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200'
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 --no-unpack 'https://qurator-data.de/mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' 'mirror/github.com/tesseract-ocr/tessdata_best/archive/'
}
. $self_dir/qurator_data_lib.sh
handle_data