NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Fix the initialization of the TesseractOcrModel (#935)

Browse Source 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
This commit is contained in:
Nikos Livathinos 2025-02-11 12:27:12 +01:00 committed by GitHub
parent de462090e7
commit c47ae700ec
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
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.scale = 3 # multiplier for 72 dpi == 216 dpi.
self.reader = None self.reader = None
self.osd_reader = None self.osd_reader = None
self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
if self.enabled: if self.enabled:
install_errmsg = ( install_errmsg = (
@ -57,8 +58,6 @@ class TesseractOcrModel(BaseOcrModel):
_log.debug("Initializing TesserOCR: %s", tesseract_version) _log.debug("Initializing TesserOCR: %s", tesseract_version)
lang = "+".join(self.options.lang) lang = "+".join(self.options.lang)
self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
if any([l.startswith("script/") for l in self._tesserocr_languages]): if any([l.startswith("script/") for l in self._tesserocr_languages]):
self.script_prefix = "script/" self.script_prefix = "script/"
else: else: