| !pip install transformers | |
| from transformers import TrOCRProcessor, VisionEncoderDecoderModel | |
| from PIL import Image | |
| import requests | |
| url = 'https://fki.tic.heia-fr.ch/static/img/a01-122-02-00.jpg' | |
| processor = TrOCRProcessor.from_pretrained('JerryWu/trocr-printed-model') | |
| model = VisionEncoderDecoderModel.from_pretrained('JerryWu/trocr-printed-model') | |
| pixel_values = processor(images=image, return_tensors="pt").pixel_values | |
| image = Image.open(requests.get(url, stream=True).raw).convert("RGB") | |
| generated_ids = model.generate(pixel_values) | |
| generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] | |
| print(generated_text) |