Update app.py

app.py

@@ -2,27 +2,29 @@ import gradio as gr
 from transformers import pipeline
 from IPython.display import Audio as IPythonAudio
 
-pipe = pipeline("image-to-text",
+itt_pipe = pipeline("image-to-text",
                 model="Salesforce/blip-image-captioning-base")
 
 
-text = pipe(input)
+text = itt_pipe(input)
+
+
 tts_pipe = pipeline("text-to-speech",
                     model="kakao-enterprise/vits-ljs")
 
+
+narrated_text = tts_pipe(tts_pipe[0]['generated_text'])
+
+def launch(text):
+    out = tts_pipe(text)
+    audio = IPythonAudio(out["audio"][0],
+             rate=out["sampling_rate"])
+    return audio
+    
 iface = gr.Interface(launch,
                      inputs=gr.Image(type='pil'),
                      outputs="text")
 
-
-narrated_text = tts_pipe(text)
-
-IPythonAudio(narrated_text["audio"][0],
-             rate=narrated_text["sampling_rate"])
-
-def launch(input):
-    out = pipe(input)
-    return out[0]['generated_text']
     
 iface.launch()