CaesarHandwriting/caesarhandwriting.py

from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
import requests

# load image from the IAM database
class CaesarHandWriting:
    def __init__(self) -> None:
        self.processor = TrOCRProcessor.from_pretrained('microsoft/trocr-large-handwritten')
        self.model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-large-handwritten')
    def translate(self,url):
        image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
        pixel_values = self.processor(images=image, return_tensors="pt").pixel_values
        generated_ids = self.model.generate(pixel_values)
        generated_text = self.processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
        return generated_text