Update app.py

app.py

@@ -1,33 +1,58 @@
 import torch
 from transformers import pipeline
 from PIL import Image
-from scipy.io import wavfile
 import gradio as gr
-import numpy as np
+import requests
+from io import BytesIO
+import os
+
 # Specify the device (CPU or GPU)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 # Load the image-to-text pipeline
 caption_image = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large", device=device)
-# Load the image-to-text pipeline with the vit-gpt2 model
-#caption_pipeline = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning", device=device)
-
-# Load the text-to-speech pipeline
-narrator = pipeline("text-to-speech", model="kakao-enterprise/vits-ljs", device=device)
-
 
+# URLs of the images
+image_urls = [
+    "https://github.com/Walid-Ahmed/ML_Datasets/blob/master/image1.jpeg?raw=true",
+    "https://github.com/Walid-Ahmed/ML_Datasets/blob/master/image2.jpeg?raw=true",
+    "https://github.com/Walid-Ahmed/ML_Datasets/blob/master/image3.jpeg?raw=true"
+]
+
+# Directory to save images
+save_dir = "example_images"
+os.makedirs(save_dir, exist_ok=True)
+
+# Function to download images
+def download_image(url, filename):
+    response = requests.get(url)
+    if response.status_code == 200:
+        with open(filename, "wb") as f:
+            f.write(response.content)
+        return filename
+    else:
+        print(f"Failed to download: {url}")
+        return None
+
+# Download images
+example_images = []
+for idx, url in enumerate(image_urls):
+    img_path = os.path.join(save_dir, f"image{idx+1}.jpeg")
+    if not os.path.exists(img_path):  # Avoid redownloading if already exists
+        download_image(url, img_path)
+    example_images.append(img_path)
+
+# Function to process the image
 def process_image(image):
-    # Generate the caption
     caption = caption_image(image)[0]['generated_text']
-
-
     return caption
 
-# Create Gradio interface
+# Create Gradio interface with example images
 iface = gr.Interface(
     fn=process_image,
     inputs=gr.Image(type="pil"),
-    outputs=[gr.Textbox(label="Generated Caption")]
+    outputs=gr.Textbox(label="Generated Caption"),
+    examples=example_images  # Use downloaded images as examples
 )
 
 # Launch the interface