mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-30 14:04:27 +00:00
feat(ocr): Add OnnxTR as possible OCR engine
Signed-off-by: felix <felixdittrich92@gmail.com>
This commit is contained in:
parent
87fa9ae7a4
commit
f6560cf662
@ -5,6 +5,7 @@ from docling.datamodel.base_models import InputFormat
|
|||||||
from docling.datamodel.pipeline_options import (
|
from docling.datamodel.pipeline_options import (
|
||||||
EasyOcrOptions,
|
EasyOcrOptions,
|
||||||
OcrMacOptions,
|
OcrMacOptions,
|
||||||
|
OnnxtrOcrOptions,
|
||||||
PdfPipelineOptions,
|
PdfPipelineOptions,
|
||||||
RapidOcrOptions,
|
RapidOcrOptions,
|
||||||
TesseractCliOcrOptions,
|
TesseractCliOcrOptions,
|
||||||
@ -21,8 +22,9 @@ def main():
|
|||||||
pipeline_options.do_table_structure = True
|
pipeline_options.do_table_structure = True
|
||||||
pipeline_options.table_structure_options.do_cell_matching = 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 = EasyOcrOptions(force_full_page_ocr=True)
|
||||||
|
# ocr_options = OnnxtrOcrOptions(force_full_page_ocr=True)
|
||||||
# ocr_options = TesseractOcrOptions(force_full_page_ocr=True)
|
# ocr_options = TesseractOcrOptions(force_full_page_ocr=True)
|
||||||
# ocr_options = OcrMacOptions(force_full_page_ocr=True)
|
# ocr_options = OcrMacOptions(force_full_page_ocr=True)
|
||||||
# ocr_options = RapidOcrOptions(force_full_page_ocr=True)
|
# ocr_options = RapidOcrOptions(force_full_page_ocr=True)
|
||||||
|
Loading…
Reference in New Issue
Block a user