Install ghostscript fonts (urw-base35) for OCR of PDFs with non-embedded fonts; fuller OCR error text
This commit is contained in:
@@ -3,7 +3,7 @@
|
||||
set -euo pipefail
|
||||
export DEBIAN_FRONTEND=noninteractive
|
||||
apt-get update -qq
|
||||
apt-get install -y -qq --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ocrmypdf ghostscript \
|
||||
apt-get install -y -qq --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ocrmypdf ghostscript fonts-urw-base35 \
|
||||
python3 python3-venv python3-pip git curl ca-certificates
|
||||
python3 -m venv .venv
|
||||
.venv/bin/pip install -q --disable-pip-version-check -r _pipeline/requirements.txt
|
||||
|
||||
Reference in New Issue
Block a user