G1Gru/TrOCR_StreetViewText

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

model_name = "https://huggingface.co/G1Gru/TrOCR_StreetViewText"
processor = TrOCRProcessor.from_pretrained(model_name)
model = VisionEncoderDecoderModel.from_pretrained(model_name)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

image = Image.open("path/to/your/image.jpg").convert("RGB")

pixel_values = processor(images=image, return_tensors="pt").pixel_values.to(device)


generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]