70 lines
2.5 KiB
Bash
70 lines
2.5 KiB
Bash
|
#!/usr/bin/env bash
|
||
|
|
#
|
||
|
|
# fetch_ocr_model.sh — download and prepare the embedded OCR recognition model.
|
||
|
|
#
|
||
|
|
# RUN THIS ON YOUR DEV MACHINE. It downloads the PaddleOCR PP-OCRv4 mobile
|
||
|
|
# recognition inference model + the character dictionary, converts the Paddle
|
||
|
|
# inference model to ONNX, and places the results as:
|
||
|
|
#
|
||
|
|
# assets/models/ocr/rec.onnx
|
||
|
|
# assets/models/ocr/ppocr_keys_v1.txt
|
||
|
|
#
|
||
|
|
# These files are intentionally NOT committed; the app treats their absence as
|
||
|
|
# a clean no-op (OCR falls back to the native backend or returns nothing).
|
||
|
|
#
|
||
|
|
# Requirements: bash, curl, tar, and paddle2onnx (pip install paddle2onnx).
|
||
|
|
#
|
||
|
|
# proxy: export HTTPS_PROXY=http://127.0.0.1:7890 (and HTTP_PROXY) if you are
|
||
|
|
# behind a firewall/GFW that blocks the download hosts.
|
||
|
|
|
||
|
|
set -euo pipefail
|
||
|
|
|
||
|
|
# Resolve repo root relative to this script so it works from any cwd.
|
||
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||
|
|
REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
|
||
|
|
OUT_DIR="${REPO_ROOT}/assets/models/ocr"
|
||
|
|
WORK_DIR="$(mktemp -d)"
|
||
|
|
|
||
|
|
# Canonical PaddleOCR sources. Swap to the en_ variant for English-only.
|
||
|
|
REC_INFER_URL="https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_rec_infer.tar"
|
||
|
|
# REC_INFER_URL="https://paddleocr.bj.bcebos.com/PP-OCRv4/english/en_PP-OCRv4_rec_infer.tar"
|
||
|
|
KEYS_URL="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/main/ppocr/utils/ppocr_keys_v1.txt"
|
||
|
|
|
||
|
|
cleanup() { rm -rf "${WORK_DIR}"; }
|
||
|
|
trap cleanup EXIT
|
||
|
|
|
||
|
|
mkdir -p "${OUT_DIR}"
|
||
|
|
|
||
|
|
echo "==> Downloading recognition inference model"
|
||
|
|
curl -fL "${REC_INFER_URL}" -o "${WORK_DIR}/rec_infer.tar"
|
||
|
|
|
||
|
|
echo "==> Extracting"
|
||
|
|
tar -xf "${WORK_DIR}/rec_infer.tar" -C "${WORK_DIR}"
|
||
|
|
# The tarball extracts into a single directory; find it.
|
||
|
|
MODEL_DIR="$(find "${WORK_DIR}" -maxdepth 1 -type d -name '*_rec_infer' | head -n1)"
|
||
|
|
if [[ -z "${MODEL_DIR}" ]]; then
|
||
|
|
echo "ERROR: could not locate the extracted *_rec_infer directory" >&2
|
||
|
|
exit 1
|
||
|
|
fi
|
||
|
|
|
||
|
|
echo "==> Downloading character dictionary"
|
||
|
|
curl -fL "${KEYS_URL}" -o "${OUT_DIR}/ppocr_keys_v1.txt"
|
||
|
|
|
||
|
|
echo "==> Converting Paddle inference model to ONNX (requires paddle2onnx)"
|
||
|
|
if ! command -v paddle2onnx >/dev/null 2>&1; then
|
||
|
|
echo "ERROR: paddle2onnx not found. Install with: pip install paddle2onnx" >&2
|
||
|
|
exit 1
|
||
|
|
fi
|
||
|
|
|
||
|
|
paddle2onnx \
|
||
|
|
--model_dir "${MODEL_DIR}" \
|
||
|
|
--model_filename inference.pdmodel \
|
||
|
|
--params_filename inference.pdiparams \
|
||
|
|
--save_file "${OUT_DIR}/rec.onnx" \
|
||
|
|
--opset_version 14 \
|
||
|
|
--enable_onnx_checker True
|
||
|
|
|
||
|
|
echo "==> Done:"
|
||
|
|
echo " ${OUT_DIR}/rec.onnx"
|
||
|
|
echo " ${OUT_DIR}/ppocr_keys_v1.txt"
|