Update app.py

app.py

@@ -13,23 +13,24 @@ text = gr.Interface(
   outputs=gr.Image(label="Text describe the image",
                    type="pil")
 )
-
+text.launch()
+print(text)
 #text = itt_pipe(input)
 
 
-tts_pipe = pipeline("text-to-speech",
-                    model="kakao-enterprise/vits-ljs")
+#tts_pipe = pipeline("text-to-speech",
+#                    model="kakao-enterprise/vits-ljs")
 
 
-narrated_text = tts_pipe(tts_pipe[0]['generated_text'])
+#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
+#def launch(text):
+#    out = tts_pipe(text)
+#    audio = IPythonAudio(out["audio"][0],
+#             rate=out["sampling_rate"])
+#    return audio
     
-iface = gr.Interface(launch,
+#iface = gr.Interface(launch,
                      inputs=gr.Image(type='pil'),
                      outputs="text")