Update app.py

app.py

@@ -67,16 +67,16 @@ def tts(txt, emotion, roma=False, length_scale=1):
         else:
             print("emotion参数不正确")
 
-        audio = net_g.infer(x_tst, x_tst_lengths, sid=sid, noise_scale=0.667, noise_scale_w=0.8, length_scale=1.2, emo=emo)[0][0,0].data.float().numpy()
-    ipd.display(ipd.Audio(audio, rate=hps.data.sampling_rate, normalize=False))
+         audio = net_g.infer(x_tst, x_tst_lengths, sid=sid, noise_scale=0.667, noise_scale_w=0.8, length_scale=1.2, emo=emo)[0][0,0].data.float().numpy()
+    return audio
 
 def generate_audio(txt, emotion):
-    tts(txt, emotion)
+    audio = tts(txt, emotion)
+    return audio
 
 input_text = gr.inputs.Textbox(label="输入文本")
 input_emotion = gr.inputs.Dropdown(choices=["random_sample"] + os.listdir(random_emotion_root), label="参考情感音频")
 output_audio = gr.outputs.Audio(type="numpy", label="合成音频")
 
-
 iface = gr.Interface(fn=generate_audio, inputs=[input_text, input_emotion], outputs=output_audio)
 iface.launch()