Update app.py

app.py

@@ -42,11 +42,15 @@ def synthesise(text):
     
     return speech.waveform
 
+def speech_to_speech_translation_fix(audio,voice_preset="v2/zh_speaker_1"):
+    synthesised_rate,synthesised_speech = speech_to_speech_translation(audio,voice_preset)
+    return synthesised_rate,synthesised_speech.T
 
 def speech_to_speech_translation(audio):
     translated_text = translate(audio)
     synthesised_speech = synthesise(translated_text)
     synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
+    synthesised_speech = speech_to_speech_translation_fix(synthesised_speech)
     return 16000, synthesised_speech