Update README.md

README.md

@@ -40,12 +40,12 @@ Use the code below to get started with the model.
 import requests
 from PIL import Image
 
-from transformers import AutoTokenizer, ViTImageProcessor, VisionEncoderDecoderModel
+from transformers import AutoTokenizer, AutoImageProcessor, VisionEncoderDecoderModel
 
 # load a fine-tuned image captioning model and corresponding tokenizer and image processor
 model = VisionEncoderDecoderModel.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
 tokenizer = AutoTokenizer.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
-image_processor = ViTImageProcessor.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
+image_processor = AutoImageProcessor.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
 
 # perform inference on an image
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"