mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-30 14:04:27 +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 2025-03-25 08:38:13 +01:00
parent 98496fafcc
commit e74d229d4b
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pyproject.toml
View File

@ -72,7 +72,7 @@ openpyxl = "^3.1.5"
lxml = ">=4.0.0,<6.0.0" lxml = ">=4.0.0,<6.0.0"
ocrmac = { version = "^1.0.0", markers = "sys_platform == 'darwin'", optional = true } ocrmac = { version = "^1.0.0", markers = "sys_platform == 'darwin'", optional = true }
rapidocr-onnxruntime = { version = "^1.4.0", optional = true, markers = "python_version < '3.13'" } rapidocr-onnxruntime = { version = "^1.4.0", optional = true, markers = "python_version < '3.13'" }
onnxtr = { extras= ["gpu"], version = "^0.6.2", optional = true, markers = "python_version >= '3.10'" } onnxtr = { extras = ["gpu"], version = "^0.6.2", optional = true, markers = "python_version >= '3.10' and python_version < '3.13'" }
onnxruntime = [ onnxruntime = [
# 1.19.2 is the last version with python3.9 support, # 1.19.2 is the last version with python3.9 support,
# see https://github.com/microsoft/onnxruntime/releases/tag/v1.20.0 # see https://github.com/microsoft/onnxruntime/releases/tag/v1.20.0

4
tests/test_e2e_ocr_conversion.py
View File

@ -74,8 +74,8 @@ def test_e2e_conversions():
engines.append(RapidOcrOptions()) engines.append(RapidOcrOptions())
engines.append(RapidOcrOptions(force_full_page_ocr=True)) engines.append(RapidOcrOptions(force_full_page_ocr=True))
# onnxtr is only available for Python >=3.10 # onnxtr is only available for Python >=3.10 and <3.13
if sys.version_info >= (3, 10): if sys.version_info >= (3, 10) and sys.version_info < (3, 13):
engines.append(OnnxtrOcrOptions()) engines.append(OnnxtrOcrOptions())
engines.append(OnnxtrOcrOptions(force_full_page_ocr=True)) engines.append(OnnxtrOcrOptions(force_full_page_ocr=True))