Update app.py

app.py

@@ -36,7 +36,7 @@ def speech_to_speech_translation(audio):
     translated_text = translate(audio)
     synthesised_speech = synthesise(translated_text)
     synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
-    return [(16000, synthesised_speech), translated_text]
+    return (16000, synthesised_speech)
 
 
 title = "Cascaded STST"
@@ -52,7 +52,7 @@ demo = gr.Blocks()
 mic_translate = gr.Interface(
     fn=speech_to_speech_translation,
     inputs=gr.Audio(source="microphone", type="filepath"),
-    outputs=[gr.Audio(label="Generated Speech", type="numpy"), gr.Textbox()],
+    outputs=gr.Audio(label="Generated Speech", type="numpy"),
     title=title,
     description=description,
 )
@@ -60,7 +60,7 @@ mic_translate = gr.Interface(
 file_translate = gr.Interface(
     fn=speech_to_speech_translation,
     inputs=gr.Audio(source="upload", type="filepath"),
-    outputs=[gr.Audio(label="Generated Speech", type="numpy"), gr.Textbox()],
+    outputs=gr.Audio(label="Generated Speech", type="numpy"),
     examples=[["./example.wav"]],
     title=title,
     description=description,