a

app.py

@@ -1,11 +1,15 @@
 import gradio as gr
 from transformers import ViltProcessor, ViltForQuestionAnswering
 import torch
+
+import httpcore
+setattr(httpcore, 'SyncHTTPTransport', 'AsyncHTTPProxy') 
+
 from googletrans import Translator
 from googletrans import LANGCODES
 import re
 
-torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg')
+torch.hub.download_url_to_file('https://media.istockphoto.com/id/1174602891/photo/two-monkeys-mom-and-cub-eat-bananas.jpg?s=612x612&w=0&k=20&c=r7VXi9d1wHhyq3iAk9D2Z3yTZiOJMlLNtjdVRBEjG7g=', 'monkeys.jpg')
 
 processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
@@ -77,7 +81,7 @@ def main(image, text):
 image = gr.inputs.Image(type="pil")
 question = gr.inputs.Textbox(label="Question")
 answer = gr.outputs.Textbox(label="Predicted answer")
-examples = [["cats.jpg", "How many cats are there, in French?"]]
+examples = [["monkeys.jpg", "How many monkeys are there, in French?"]]
 
 title = "Cross-lingual VQA"
 description = "ViLT (Vision and Language Transformer), fine-tuned on VQAv2 "