Update app.py

app.py

@@ -34,8 +34,8 @@ model = AutoModelForCausalLM.from_pretrained(
 wav2vec2_processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
 wav2vec2_model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
 
-vit_model = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224')
-vit_feature_extractor = ViTFeatureExtractor.from_pretrained('ohidaoui/monuments-morocco-v1')
+vit_model = ViTForImageClassification.from_pretrained('ohidaoui/monuments-morocco-v1')
+vit_feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224')
 
 
 # Function to handle text input