---
license: apache-2.0
tags:
- document-understanding
- ocr
- prescription
- medical-ocr
- donut
library_name: transformers
---

# Prescription OCR Reader — Donut

Stage 2 ng YOLO+Donut prescription OCR pipeline.

## Usage
```python
from transformers import DonutProcessor, VisionEncoderDecoderModel
from huggingface_hub import hf_hub_download
from PIL import Image

processor = DonutProcessor.from_pretrained("ajmaclin/prescription-donut-ocr")
model     = VisionEncoderDecoderModel.from_pretrained("ajmaclin/prescription-donut-ocr")

image        = Image.open("prescription_crop.jpg")
pixel_values = processor(image, return_tensors="pt").pixel_values
outputs      = model.generate(pixel_values, max_length=256)
result       = processor.batch_decode(outputs, skip_special_tokens=True)[0]
print(result)
```