Update app.py

app.py

@@ -5,7 +5,6 @@ from PIL import Image
 import scipy.io.wavfile
 
 # Load the MusicGen model
-musicgen = pipeline("text-to-audio", model="facebook/musicgen-small")
 
 # Load the StreetCLIP model
 model = CLIPModel.from_pretrained("geolocal/StreetCLIP")
@@ -13,7 +12,7 @@ processor = CLIPProcessor.from_pretrained("geolocal/StreetCLIP")
 
 labels = ['Albania', 'Andorra', 'Argentina', 'Australia', 'Austria', 'Bangladesh', 'Belgium', 'Bermuda', 'Bhutan', 'Bolivia', 'Botswana', 'Brazil', 'Bulgaria', 'Cambodia', 'Canada', 'Chile', 'China', 'Colombia', 'Croatia', 'Czech Republic', 'Denmark', 'Dominican Republic', 'Egypt', 'Ecuador', 'Estonia', 'Finland', 'France', 'Germany', 'Ghana', 'Greece', 'Greenland', 'Guam', 'Guatemala', 'Hungary', 'Iceland', 'India', 'Indonesia', 'Ireland', 'Israel', 'Italy', 'Japan', 'Jordan', 'Kenya', 'Kyrgyzstan', 'Laos', 'Latvia', 'Lesotho', 'Lithuania', 'Luxembourg', 'Macedonia', 'Madagascar', 'Malaysia', 'Malta', 'Mexico', 'Monaco', 'Mongolia', 'Montenegro', 'Netherlands', 'New Zealand', 'Nigeria', 'Norway', 'Pakistan', 'Palestine', 'Peru', 'Philippines', 'Poland', 'Portugal', 'Puerto Rico', 'Romania', 'Russia', 'Rwanda','Saudi Arabia', 'Senegal', 'Serbia', 'Singapore', 'Slovakia', 'Slovenia', 'South Africa', 'South Korea', 'Spain', 'Sri Lanka', 'Swaziland', 'Sweden', 'Switzerland', 'Syria','Taiwan', 'Thailand', 'Tunisia', 'Turkey', 'Uganda', 'Ukraine', 'United Arab Emirates', 'United Kingdom', 'United States', 'Uruguay']
 
-def process_image(image, audio_path="musicgen_out.wav"):
+def process_image(image):
     # Ensure the image is in the correct format
     if isinstance(image, str):
         image = Image.open(image)
@@ -33,18 +32,15 @@ def process_image(image, audio_path="musicgen_out.wav"):
     country = labels[country_index]
     print(country)
     # Generate music based on the country
-    music_description = f"Traditional music from {country}"
-    music = musicgen(music_description, forward_params={"do_sample": True})
 
     # Save the generated music to the specified path
-    scipy.io.wavfile.write(audio_path, rate=music["sampling_rate"], data=music["audio"])
 
     # Return the country and the path to the generated music
-    return country, audio_path
+    return country
 
 # Define the Gradio interface
 inputs = gr.Image(type="pil", label="Upload a photo (تحميل صورة)")
-outputs = [gr.Textbox(label="Country (البلد)"), gr.Audio(label="Generated Music (الموسيقى المولدة)")]
+outputs = [gr.Textbox(label="Country (البلد)")]
 
 iface = gr.Interface(
     fn=process_image,