Image-Text-to-Text
ONNX
PaddleOCR
English
Chinese
Russian
paddleocr_vl
onnxruntime
ocr
document-parse
ERNIE4.5
conversational
custom_code
Instructions to use hb-dev/PaddleOCR-VL-1.6-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PaddleOCR
How to use hb-dev/PaddleOCR-VL-1.6-ONNX 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="hb-dev/PaddleOCR-VL-1.6-ONNX") 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
Download tokenizer.json from hb-dev/PaddleOCR-VL-1.6-ONNX: direct link, hf CLI and curl.
- Browser
- Download file 11.2 MB
-
https://huggingface.co/hb-dev/PaddleOCR-VL-1.6-ONNX/resolve/main/tokenizer.json
- Command line
-
hf download hf://hb-dev/PaddleOCR-VL-1.6-ONNX/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/hb-dev/PaddleOCR-VL-1.6-ONNX/resolve/main/tokenizer.json
11.2 MB
- Xet hash:
- b81bcd686de434961e297c5797a82ccd6eac2b980de03ea39aaa0623b80f8cbd
- Size of remote file:
- 11.2 MB
- SHA256:
- c8a215a59183d0d0781adc33bacd3ce6162716f7fd568fb30234a74d69803a7d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.