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

🚧 Do not add data to container image

Browse source
This commit is contained in:
Gerber, Mike 2023-02-10 17:13:32 +01:00
parent 257a568933
commit 252a125ed2
6 changed files with 0 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

7
Dockerfile-ocrd_tesserocr
View file

@ -17,13 +17,6 @@ RUN add-apt-repository ppa:alex-p/tesseract-ocr && \
apt-get clean && rm -rf /var/lib/apt/lists/*
# Copy OCR models
RUN mkdir -p $TESSDATA_PREFIX
ADD data/mirror/github.com/tesseract-ocr/tessdata_best/archive/${TESSDATA_BEST_VERSION}-repacked.tar.gz $TESSDATA_PREFIX/
COPY data/tesseract-models/GT4HistOCR/GT4HistOCR_2000000.traineddata $TESSDATA_PREFIX/
RUN curl -sSL -O https://ub-backup.bib.uni-mannheim.de/~stweil/ocrd-train/data/Fraktur_5000000/tessdata_fast/Fraktur_50000000.502_198857.traineddata && \
mv *.traineddata $TESSDATA_PREFIX/
# Build pip installable stuff
RUN ${PIP_INSTALL} \
"ocrd_tesserocr == ${OCRD_TESSEROCR_VERSION}"