Update app.py

app.py

@@ -36,9 +36,9 @@ def chat_hf(audio, custom_token, language):
     
     # to voice
     if language == 'cn' or 'jp':
-        text = infer.clean_text(gpt_response)
-        voice_out = infer.infer(text, net_g_ms, 2, "demo")
-        #voice_out = (hps.data.sampling_rate, audio)
+        #text = infer.clean_text(gpt_response)
+        audio = infer.infer(gpt_response, net_g_ms, 2, "demo")
+        voice_out = (hps.data.sampling_rate, audio)
     else:
         with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
             coquiTTS.get_tts(gpt_response, fp, speaker = {"language" : language})