Remove synthetic training path and add fine-text OCR option

ocr_compare/classic_worker.py

@@ -2,10 +2,10 @@
 
 from __future__ import annotations
 
+import argparse
 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()
@@ -13,9 +13,12 @@ MODELS = ROOT / "official_models"
 
 
 def main() -> None:
-    if len(sys.argv) != 3:
-        raise SystemExit(2)
-    image, output = map(Path, sys.argv[1:])
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("image", type=Path)
+    parser.add_argument("output", type=Path)
+    parser.add_argument("--fine-text", action="store_true")
+    args = parser.parse_args()
+    image, output = args.image, args.output
     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():
@@ -30,6 +33,8 @@ def main() -> None:
         use_doc_orientation_classify=False,
         use_doc_unwarping=False,
         use_textline_orientation=False,
+        text_det_limit_side_len=2048 if args.fine_text else 960,
+        text_det_limit_type="max",
         device="cpu",
     )
     results = list(engine.predict(str(image)))