Image-Text-to-Text
PaddleOCR
Safetensors
English
Chinese
multilingual
paddleocr_vl
ERNIE4.5
PaddlePaddle
image-to-text
ocr
document-parse
layout
table
formula
chart
conversational
custom_code
Eval Results
Instructions to use PaddlePaddle/PaddleOCR-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PaddleOCR
How to use PaddlePaddle/PaddleOCR-VL with PaddleOCR:
# See https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PaddleOCR-VL.html to installation from paddleocr import PaddleOCRVL pipeline = PaddleOCRVL(pipeline_version="v1") output = pipeline.predict("path/to/document_image.png") for res in output: res.print() res.save_to_json(save_path="output") res.save_to_markdown(save_path="output") - Notebooks
- Google Colab
- Kaggle
Are there plans to switch from pp-doclayoutv2 to pp-doclayoutv3 in PaddleOCR-VL?
#86
by sogm1 - opened
Hello,
I’ve been using PaddleOCR-VL and it’s been working really well for our use case—thank you for the great solution.
According to the paper (and what I see in the current package), it seems that pp-doclayoutv2 is currently integrated/bundled within PaddleOCR-VL.
Do you have any plans or a timeline to upgrade/switch to pp-doclayoutv3 in PaddleOCR-VL?
If an update is planned, I’d also appreciate any details on expected release timing or compatibility considerations.
Thank you.
Today i got news you guys launch paddle-ocr-vl-1.5 moduled to pp-doclayoutv3 :)
sogm1 changed discussion status to closed