Update app.py

app.py

@@ -1,24 +1,32 @@
 import gradio as gr
 from transformers import pipeline
+from IPython.display import Audio as IPythonAudio
 
 pipe = pipeline("image-to-text",
                 model="Salesforce/blip-image-captioning-base")
 
-def launch(input):
-    out = pipe(input)
-    return out[0]['generated_text']
+
+text = pipe(input)
+tts_pipe = pipeline("text-to-speech",
+                    model="kakao-enterprise/vits-ljs")
 
 iface = gr.Interface(launch,
                      inputs=gr.Image(type='pil'),
                      outputs="text")
 
-tts_pipe = pipeline("text-to-speech",
-                    model="kakao-enterprise/vits-ljs")
-text = iface.launch()
 
 narrated_text = tts_pipe(text)
 
-from IPython.display import Audio as IPythonAudio
-
 IPythonAudio(narrated_text["audio"][0],
-             rate=narrated_text["sampling_rate"])
+             rate=narrated_text["sampling_rate"])
+
+def launch(input):
+    out = pipe(input)
+    return out[0]['generated_text']
+    
+iface.launch()
+
+
+
+
+