Update app.py

app.py

@@ -42,7 +42,7 @@ def speech_to_speech_translation(audio):
     synthesised_speech = synthesise(translated_text)
     synthesised_speech = (
         synthesised_speech.numpy() * 32767).astype(np.int16)
-    return 16000, synthesised_speech
+    return "", synthesised_speech
 
 def predict(transType, language, audio, audio_mic = None):
         print("debug1:", audio,"debug2", audio_mic)
@@ -50,7 +50,7 @@ def predict(transType, language, audio, audio_mic = None):
             audio = audio_mic
         audio = audio[1]
         if transType == "Text":
-            return translate(audio)
+            return translate(audio), None
         if transType == "Audio":
             return speech_to_speech_translation(audio)
             
@@ -76,7 +76,7 @@ demo = gr.Interface(
         gr.Audio(label="Record an audio", sources="microphone", type="numpy"),
     ],
     outputs=[
-        gr.Text(label="Text translation"),gr.Audio(label="Audio translation")
+        gr.Text(label="Text translation"),gr.Audio(label="Audio translation",type = "numpy")
     ],
     title=title,
     description=description,