🐛 Add tessdata_best Tesseract models again

This commit is contained in:
Gerber, Mike 2020-03-02 12:47:46 +01:00
parent 5e8cd47798
commit 88c29cef68
2 changed files with 6 additions and 4 deletions

View file

@ -60,11 +60,13 @@ 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
COPY data/tesseract-models/GT4HistOCR/GT4HistOCR_2000000.traineddata $TESSDATA_PREFIX/
COPY data/textline_detection /var/lib/textline_detection
RUN tesseract --list-langs
# Install requirements
COPY requirements.txt /tmp/