Update app.py

app.py

@@ -37,13 +37,12 @@ def infer(image):
     print(most_close, diff_value)
     if most_close >= area_thres and diff_value >= 0.5:
         voice_bot = tts(defaul_bot_voice, language="ja")
-    return voice_bot, out_img
+    return out_img, voice_bot
     
 iface = gr.Interface(
     fn=infer,
     title="aisatsu api",
     inputs=[gr.Image(label="image", type="pil", shape=(960, 640))],
-    outputs=[gr.Image(label="output image"), gr.Textbox(label="output voice"))],
-    cache_examples=True,
+    outputs=[gr.Image(label="output image"), gr.Textbox(label="output voice")],
     article = "Author: <a href=\"https://huggingface.co/vumichien\">Vu Minh Chien</a>.",
-    examples=examples).launch(enable_queue=True)
+).launch(enable_queue=True, debug=True, share=True)