Update app.py

app.py

@@ -3,7 +3,7 @@ import os
 import cv2
 import tempfile
 from PIL import Image
-from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer, pipeline
+from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer, pipeline
 import torch
 import pandas as pd
 from nltk.corpus import wordnet
@@ -16,7 +16,8 @@ nltk.download('omw-1.4')
 # Load the pre-trained model for image captioning
 model_name = "NourFakih/Vit-GPT2-COCO2017Flickr-85k-09"
 model = VisionEncoderDecoderModel.from_pretrained(model_name)
-feature_extractor = ViTFeatureExtractor.from_pretrained(model_name)
+model.config.pad_token_id
+feature_extractor = ViTImageProcessor.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)