mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-29 21:44:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(ocr): Add OnnxTR as possible OCR engine

Browse Source 
Signed-off-by: felix <felixdittrich92@gmail.com>
This commit is contained in:
felix 2025-03-22 13:36:26 +01:00
parent 87fa9ae7a4
commit f6560cf662
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/examples/full_page_ocr.py
View File

@ -5,6 +5,7 @@ from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import (
EasyOcrOptions,
OcrMacOptions,
OnnxtrOcrOptions,
PdfPipelineOptions,
RapidOcrOptions,
TesseractCliOcrOptions,
@ -21,8 +22,9 @@ def main():
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
# Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions, OcrMacOptions(Mac only), RapidOcrOptions
# Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions, OcrMacOptions(Mac only), RapidOcrOptions, OnnxtrOcrOptions
# ocr_options = EasyOcrOptions(force_full_page_ocr=True)
# ocr_options = OnnxtrOcrOptions(force_full_page_ocr=True)
# ocr_options = TesseractOcrOptions(force_full_page_ocr=True)
# ocr_options = OcrMacOptions(force_full_page_ocr=True)
# ocr_options = RapidOcrOptions(force_full_page_ocr=True)