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 2025-03-31 14:31:47 +02:00
parent 4cd2ec5515
commit 1f9872c8ae
2 changed files with 8065 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8061
poetry.lock generated Normal file
View File

File diff suppressed because it is too large Load Diff

6
pyproject.toml
View File

@ -76,8 +76,8 @@ onnxtr = { extras = ["gpu"], version = "^0.6.2", optional = true, markers = "pyt
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
{ version = "^1.7.0", optional = true, markers = "python_version < '3.10'" }, { version = ">=1.7.0,<1.20.0", optional = true, markers = "python_version < '3.10'" },
{ version = ">=1.7.0,<2.0.0", optional = true, markers = "python_version >= '3.10'" }, { version = "^1.7.0", optional = true, markers = "python_version >= '3.10'" },
] ]
transformers = [ transformers = [
@ -149,6 +149,7 @@ torchvision = [
] ]
[tool.poetry.extras] [tool.poetry.extras]
onnxtr = ["onnxtr"]
tesserocr = ["tesserocr"] tesserocr = ["tesserocr"]
ocrmac = ["ocrmac"] ocrmac = ["ocrmac"]
vlm = ["transformers", "accelerate"] vlm = ["transformers", "accelerate"]
@ -193,6 +194,7 @@ module = [
"docling_ibm_models.*", "docling_ibm_models.*",
"easyocr.*", "easyocr.*",
"ocrmac.*", "ocrmac.*",
"onnxtr.*",
"mlx_vlm.*", "mlx_vlm.*",
"lxml.*", "lxml.*",
"huggingface_hub.*", "huggingface_hub.*",