occam razor once again, ugly but functional solution

app.py

@@ -1,53 +1,5 @@
 import gradio as gr
-from transformers import pipeline
 
-
-TITLE = 'FaVQA - Fashion-related Visual Question Answering'
-DESCRIPTION = 'Fine-tuned ViLT with DeepFashion dataset images for VQA task'
-ARTICLE = 'COLOCAR DESCRIÇÃO AQUI MONA'
-
-
-##########################################################
-#                 WRAPPER FUNCTION
-##########################################################
-def predict(txt, img):
-  pipe = pipeline(model='yanka9/vilt_finetuned_deepfashionVQA_v2')
-  output = pipe(image=img, question=txt, top_k=2)
-  result = {item['answer']:item['score'] for item in output}
-
-  return result
-
-##########################################################
-#                  COMPONENTS
-##########################################################
-txt_input = gr.Textbox(
-  max_lines=2,
-  label='Question',
-  show_copy_button=True
-)
-
-img_input = gr.Image(
-  sources=['upload', 'clipboard'],
-  type='pil'
-)
-
-label_output = gr.Label(
-  label='Answer',
-  num_top_classes=2
-)
-
-##########################################################
-#                  BUILDER
-##########################################################
-demo = gr.Interface(
-  fn=predict,
-  title=TITLE,
-  description=DESCRIPTION,
-  article=ARTICLE,
-  theme='gradio/monochrome',
-  allow_flagging='never',
-  inputs=[txt_input, img_input],
-  outputs=label_output
-)
+demo = gr.load('yanka9/vilt_finetuned_deepfashionVQA_v2', src='models')
 
 demo.launch()