Add private local OCR comparison package

ocr_compare/classic_worker.py

@@ -0,0 +1,48 @@
+"""PP-OCRv5 Latin inference using preloaded local model directories only."""
+
+from __future__ import annotations
+
+import json
+import os
+from pathlib import Path
+import sys
+
+
+ROOT = Path(os.environ.get("OCR_MODEL_HOME", Path(__file__).resolve().parents[1] / ".cache")).expanduser().resolve()
+MODELS = ROOT / "official_models"
+
+
+def main() -> None:
+    if len(sys.argv) != 3:
+        raise SystemExit(2)
+    image, output = map(Path, sys.argv[1:])
+    detector = MODELS / "PP-OCRv5_mobile_det"
+    recognizer = MODELS / "latin_PP-OCRv5_mobile_rec"
+    if not (detector / "inference.pdiparams").is_file() or not (recognizer / "inference.pdiparams").is_file():
+        raise SystemExit(3)
+    from paddleocr import PaddleOCR
+
+    engine = PaddleOCR(
+        text_detection_model_name="PP-OCRv5_mobile_det",
+        text_detection_model_dir=str(detector),
+        text_recognition_model_name="latin_PP-OCRv5_mobile_rec",
+        text_recognition_model_dir=str(recognizer),
+        use_doc_orientation_classify=False,
+        use_doc_unwarping=False,
+        use_textline_orientation=False,
+        device="cpu",
+    )
+    results = list(engine.predict(str(image)))
+    if len(results) != 1:
+        raise RuntimeError("expected_one_page")
+    raw = results[0].json["res"]
+    lines = []
+    for text, polygon in zip(raw["rec_texts"], raw["rec_polys"]):
+        points = [[int(x), int(y)] for x, y in polygon]
+        xs, ys = zip(*points)
+        lines.append({"text": str(text), "bbox": [min(xs), min(ys), max(xs), max(ys)]})
+    output.write_text(json.dumps({"lines": lines}, ensure_ascii=False))
+
+
+if __name__ == "__main__":
+    main()