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

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

View file

@ -63,10 +63,7 @@ RUN pip3 install --no-cache-dir --upgrade pip && \
RUN mkdir -p /var/lib/calamari-models
COPY data/calamari-models/GT4HistOCR /var/lib/calamari-models/GT4HistOCR
RUN mkdir -p $TESSDATA_PREFIX
RUN curl -sSL -O https://qurator-data.de/mirror/github.com/tesseract-ocr/tessdata_best/archive/$TESSDATA_BEST_VERSION.tar.gz && \
tar xzf $TESSDATA_BEST_VERSION.tar.gz && \
mv tessdata_best-$TESSDATA_BEST_VERSION/* $TESSDATA_PREFIX/ && \
rm -rf $TESSDATA_BEST_VERSION.tar.gz
ADD data/mirror/github.com/tesseract-ocr/tessdata_best/archive/${TESSDATA_BEST_VERSION}-repacked.tar.gz $TESSDATA_PREFIX/
COPY data/tesseract-models/GT4HistOCR/GT4HistOCR_2000000.traineddata $TESSDATA_PREFIX/
COPY data/textline_detection /var/lib/textline_detection