Add truncation for inputs that are too long

app.py

@@ -52,7 +52,7 @@ def process_image(image):
     words, boxes = encoding_feature_extractor.words, encoding_feature_extractor.boxes
 
     # encode
-    encoding = tokenizer(words, boxes=boxes, return_offsets_mapping=True, return_tensors="pt")
+    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