Update app.py

app.py

@@ -14,8 +14,8 @@ class TTSWebUI:
 
     def __init__(self,
                  gpu_id="cpu",
-                 title="Controllable Text-to-Speech for over 7000 Languages",
-                 article="This is running using CPU. <br>",
+                 title="超过7000种语音 文本转语音 Text-to-Speech",
+                 article="这是使用 CPU 运行的. <br>",
                  tts_model_path=None,
                  vocoder_model_path=None,
                  embedding_gan_path=None,
@@ -33,24 +33,24 @@ class TTSWebUI:
                                                      embedding_gan_path=embedding_gan_path)
         self.iface = gr.Interface(fn=self.read,
                                   inputs=[gr.Textbox(lines=2,
-                                                     placeholder="write what you want the synthesis to read here...",
+                                                     placeholder="在这里写下您希望综合阅读的内容...",
                                                      value="What I cannot create, I do not understand.",
-                                                     label="Text input"),
+                                                     label="文本输入"),
                                           gr.Dropdown(text_selection,
                                                       type="value",
-                                                      value='English (eng)',
-                                                      label="Select the Language of the Text (type on your keyboard to find it quickly)"),
-                                          gr.Slider(minimum=0.0, maximum=0.8, step=0.1, value=0.5, label="Prosody Creativity"),
-                                          gr.Slider(minimum=0.7, maximum=1.3, step=0.1, value=1.0, label="Faster - Slower"),
-                                          gr.Slider(minimum=0, maximum=available_artificial_voices, step=1, value=16, label="Random Seed for the artificial Voice"),
-                                          gr.Slider(minimum=-10.0, maximum=10.0, step=0.1, value=0.0, label="Gender of artificial Voice"),
-                                          gr.Audio(type="filepath", show_label=True, container=True, label="[OPTIONAL] Voice to Clone (if left empty, will use an artificial voice instead)"),
+                                                      value='Bulgarian (bul)',
+                                                      label="选择文本的语言（在键盘上输入以快速找到它）"),
+                                          gr.Slider(minimum=0.0, maximum=0.8, step=0.1, value=0.5, label="创造力"),
+                                          gr.Slider(minimum=0.7, maximum=1.3, step=0.1, value=1.0, label="更快 - 更慢"),
+                                          gr.Slider(minimum=0, maximum=available_artificial_voices, step=1, value=16, label="人工语音的随机种子"),
+                                          gr.Slider(minimum=-10.0, maximum=10.0, step=0.1, value=0.0, label="人工声音的性别 女-男"),
+                                          gr.Audio(type="filepath", show_label=True, container=True, label="[可选] 克隆声音（如果留空，将使用人工声音）"),
                                           # gr.Slider(minimum=0.5, maximum=1.5, step=0.1, value=1.0, label="Pitch Variance Scale"),
                                           # gr.Slider(minimum=0.5, maximum=1.5, step=0.1, value=1.0, label="Energy Variance Scale"),
                                           # gr.Slider(minimum=-10.0, maximum=10.0, step=0.1, value=0.0, label="Voice Depth")
                                           ],
-                                  outputs=[gr.Audio(type="numpy", label="Speech"),
-                                           gr.Image(label="Visualization")],
+                                  outputs=[gr.Audio(type="numpy", label="生成音频"),
+                                           gr.Image(label="音调可视化")],
                                   title=title,
                                   allow_flagging="never",
                                   description=article