Use processor instead

app.py

@@ -14,12 +14,11 @@ os.system('pip install -q pytesseract')
 
 import gradio as gr
 import numpy as np
-from transformers import LayoutLMv2FeatureExtractor, LayoutLMv2TokenizerFast, LayoutLMv2ForTokenClassification
+from transformers import LayoutLMv2Processor, LayoutLMv2ForTokenClassification
 from datasets import load_dataset
 from PIL import Image, ImageDraw, ImageFont
 
-feature_extractor = LayoutLMv2FeatureExtractor.from_pretrained("microsoft/layoutlmv2-base-uncased")
-tokenizer = LayoutLMv2TokenizerFast.from_pretrained("microsoft/layoutlmv2-base-uncased")
+processor = LayoutLMv2Processor.from_pretrained("microsoft/layoutlmv2-base-uncased")
 model = LayoutLMv2ForTokenClassification.from_pretrained("nielsr/layoutlmv2-finetuned-funsd")
 
 # load image example
@@ -48,15 +47,10 @@ def iob_to_label(label):
 
 def process_image(image):
     width, height = image.size
-    
-    # get words, boxes
-    encoding_feature_extractor = feature_extractor(image, return_tensors="pt")
-    words, boxes = encoding_feature_extractor.words, encoding_feature_extractor.boxes
 
     # encode
     encoding = tokenizer(words, boxes=boxes, truncation=True, return_offsets_mapping=True, return_tensors="pt")
     offset_mapping = encoding.pop('offset_mapping')
-    encoding["image"] = encoding_feature_extractor.pixel_values
 
     # forward pass
     outputs = model(**encoding)