Create app.py

app.py

@@ -0,0 +1,10 @@
+from transformers import BlipForQuestionAnswering, AutoProcessor  # For the pre-trained VQA model and processor
+from PIL import Image  # For image handling
+import gradio as gr  # For creating the interface
+from gtts import gTTS  # For converting text to speech
+import os  # For file handling
+
+# Load the model and processor from Hugging Face
+model = BlipForQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base")
+processor = AutoProcessor.from_pretrained("Salesforce/blip-vqa-base")
+