fix and update tesserocr installation

Dockerfile

@@ -26,7 +26,7 @@ RUN echo "deb http://http.us.debian.org/debian stable non-free" >/etc/apt/source
   imagemagick-common imagemagick mdbtools djvulibre-bin \
   libtiff5-dev libjpeg-dev libfreetype6-dev libwebp-dev \
   libtiff-tools ghostscript librsvg2-bin jbig2dec \
-  pst-utils \
+  pst-utils libopenjp2-7-dev libgif-dev libpng-dev \
   ### tesseract
   tesseract-ocr-eng \
   tesseract-ocr-swa \
@@ -126,7 +126,7 @@ RUN mkdir /models/ && \
 COPY requirements.txt /tmp/
 #RUN pip3 install --no-cache-dir --prefer-binary --upgrade pip
 #RUN pip3 install --no-cache-dir --prefer-binary --upgrade setuptools wheel
-RUN pip3 install --no-cache-dir -r /tmp/requirements.txt
+RUN pip3 install --no-cache-dir --no-binary tesserocr -r /tmp/requirements.txt
 
 # Install spaCy models
 RUN python3 -m spacy download en_core_web_sm \

requirements.txt

@@ -8,7 +8,7 @@ languagecodes==1.1.1
 countrytagger==0.1.2
 pyicu==2.12
 google-cloud-vision==3.7.2
-tesserocr==2.6.2
+tesserocr==2.7.1
 spacy==3.6.1
 numpy<2.0.0 # pinned because otherwise spacy requires an incompatible numpy
 fingerprints==1.1.1