mirror of
https://github.com/DS4SD/docling.git
synced 2025-08-01 23:12:20 +00:00
Fix script models prefix for Linux
Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>
This commit is contained in:
parent
ce40eb7b84
commit
1f3f4be3f0
@ -57,6 +57,11 @@ class TesseractOcrModel(BaseOcrModel):
|
||||
|
||||
self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
|
||||
|
||||
if any([l.startswith("script/") for l in tesserocr_languages]):
|
||||
self.script_prefix = "script/"
|
||||
else:
|
||||
self.script_prefix = ""
|
||||
|
||||
tesserocr_kwargs = {
|
||||
"psm": tesserocr.PSM.AUTO,
|
||||
"init": True,
|
||||
@ -138,7 +143,7 @@ class TesseractOcrModel(BaseOcrModel):
|
||||
if script not in self.script_readers:
|
||||
self.script_readers[script] = tesserocr.PyTessBaseAPI(
|
||||
path=self.reader.GetDatapath(),
|
||||
lang=f"script/{script}",
|
||||
lang=f"{self.script_prefix}{script}",
|
||||
psm=tesserocr.PSM.AUTO,
|
||||
init=True,
|
||||
oem=tesserocr.OEM.DEFAULT,
|
||||
|
Loading…
Reference in New Issue
Block a user