mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 14:34:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Fix the initialization of the TesseractOcrModel

Browse Source 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
This commit is contained in:
Nikos Livathinos 2025-02-10 17:47:28 +01:00
parent de462090e7
commit cc0e64b0cb
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docling/models/tesseract_ocr_model.py
View File

@ -22,6 +22,7 @@ class TesseractOcrModel(BaseOcrModel):
self.scale = 3 # multiplier for 72 dpi == 216 dpi.
self.reader = None
self.osd_reader = None
self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
if self.enabled:
install_errmsg = (
@ -57,8 +58,6 @@ class TesseractOcrModel(BaseOcrModel):
_log.debug("Initializing TesserOCR: %s", tesseract_version)
lang = "+".join(self.options.lang)
self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
if any([l.startswith("script/") for l in self._tesserocr_languages]):
self.script_prefix = "script/"
else: