Expose rec_keys_path in RapidOcrOptions to support custom dictionaries

- Added `rec_keys_path` to `RapidOcrOptions` to align with RapidOCR's capability to use custom character dictionaries. - Passed `rec_keys_path` to `RapidOcrModel` initialization, ensuring the recognition model can load the correct dictionary (e.g., for Latin characters). Signed-off-by: Yorick Terweijden <[email protected]>
DS4SD · Jan 23, 2025 · d2f9f05 · d2f9f05
1 parent c49b352
commit d2f9f05
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 0 deletions.
diff --git a/docling/datamodel/pipeline_options.py b/docling/datamodel/pipeline_options.py
@@ -125,6 +125,7 @@ class RapidOcrOptions(OcrOptions):
     det_model_path: Optional[str] = None  # same default as rapidocr
     cls_model_path: Optional[str] = None  # same default as rapidocr
     rec_model_path: Optional[str] = None  # same default as rapidocr
+    rec_keys_path: Optional[str] = None   # same default as rapidocr
 
     model_config = ConfigDict(
         extra="forbid",

diff --git a/docling/models/rapid_ocr_model.py b/docling/models/rapid_ocr_model.py
@@ -59,6 +59,7 @@ def __init__(
                 det_model_path=self.options.det_model_path,
                 cls_model_path=self.options.cls_model_path,
                 rec_model_path=self.options.rec_model_path,
+                rec_keys_path=self.options.rec_keys_path,
             )
 
     def __call__(