arabic-audio-reader-worker / scripts /setup_baseer_ocr.sh
Syncre's picture
Deploy Arabic Audio Reader worker
2e1a095 verified
#!/usr/bin/env bash
set -euo pipefail
PYTHON_BIN="${PYTHON_BIN:-python3}"
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
VENV="$ROOT/.venv-baseer-ocr"
if [ ! -d "$VENV" ]; then
"$PYTHON_BIN" -m venv "$VENV"
fi
"$VENV/bin/python" -m pip install --upgrade pip
"$VENV/bin/python" -m pip install -r "$ROOT/requirements-baseer-ocr.txt"
"$VENV/bin/python" -c "import torch; from transformers import AutoProcessor, Qwen2VLForConditionalGeneration; import qwen_vl_utils"
echo "Baseer OCR sidecar is ready at $VENV"
echo "Use OCR_ENGINE=baseer-ocr for Arabic document OCR on short samples or a worker."