Update app.py

app.py

@@ -5,7 +5,7 @@ from PIL import Image
 import scipy.io.wavfile
 
 # Load the MusicGen model
-musicgen = pipeline("text-to-audio", model="facebook/musicgen-small")
+#musicgen = pipeline("text-to-audio", model="facebook/musicgen-small")
 
 # Load the StreetCLIP model
 model = CLIPModel.from_pretrained("geolocal/StreetCLIP")
@@ -32,18 +32,18 @@ def process_image(image, audio_path="musicgen_out.wav"):
     country = labels[country_index]
 
     # Generate music based on the country
-    music_description = f"Traditional music from {country}"
-    music = musicgen(music_description, forward_params={"do_sample": True})
+    #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,