Update app.py

app.py

@@ -29,7 +29,8 @@ 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
+    return translated_text
+    #return 16000, synthesised_speech
 
 
 title = "Cascaded STST"
@@ -53,7 +54,8 @@ 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"),
+    outputs=gr.outputs.Textbox(),
+    #outputs=gr.Audio(label="Generated Speech", type="numpy"),
     examples=[["./example.wav"]],
     title=title,
     description=description,