Update app.py

app.py

@@ -11,7 +11,9 @@ pipe = pipeline("text-to-speech", model="openai/whisper-large-v3-turbo")
 def launch(input_image):
     try:
         # Step 1: Generate caption
-        caption = captioner(input_image)[0]['generated_text']
+        out = captioner(input_image)
+        caption = out[0]['generated_text']
+        
 
         # Step 2: Synthesize speech from caption
         speech = pipe(caption)