Update app.py

app.py

@@ -49,15 +49,15 @@ def generate_caption_from_image(model, processor, image):
 # -------------------------------
 def generate_caption_tts(image):
     caption = generate_caption_from_image(model, processor, image)  # uses global model/processor
-    audio_file = text_to_audio_file(caption)
-    return caption, audio_file
+    # audio_file = text_to_audio_file(caption)
+    return caption 
 
 
 
 interface = gr.Interface(
     fn=generate_caption_tts,
     inputs=gr.Image(type="numpy"),
-    outputs=[gr.Textbox(label="Generated Caption"), gr.Audio(type="filepath", label="TTS Audio")],
+    outputs=[gr.Textbox(label="Generated Caption")],
     title="Image Captioning for Visually Impaired",
     description="Upload an image, get a caption and audio description."
 )