fix gradio on space

inference/svs/gradio/gradio_settings.yaml

@@ -2,13 +2,22 @@ title: 'DiffSinger'
 description: |
   Gradio demo for DiffSinger.
 
-  This model is trained on 5 hours single female singing voice samples of Opencpop dataset. 汉译：该模型在开源数据集Opencpop的5小时单人歌声上训练。
+  This model is trained on 5 hours single female singing voice samples of Opencpop dataset.
+
+  (该模型在开源数据集Opencpop的5小时单人歌声上训练。)
 
   Please assign pitch and duration values to each Chinese character. The corresponding pitch and duration value of each character should be separated by a | separator. It is necessary to ensure that the note window separated by the separator is consistent with the number of Chinese characters (AP or SP is also a Chinese character).
-  汉译：请给每个汉字分配音高和时值, 每个字对应的音高和时值需要用|分隔符隔开。需要保证分隔符分割出来的音符窗口与汉字个数(AP或SP也算一个汉字)一致。
+
+  (请给每个汉字分配音高和时值, 每个字对应的音高和时值需要用|分隔符隔开。需要保证分隔符分割出来的音符窗口与汉字个数(AP或SP也算一个汉字)一致。)
 
   The third example exhibits pitch value changing (C#4->C5).
-  汉译：第三个例子演示了乐谱变动 (C#4->C5)。
+
+  (第三个例子演示了乐谱变动 (C#4->C5)。)
+
+  Note: This space is running on CPU, inference times will be higher.
+
+  (该Demo是在Huggingface提供的CPU上运行的, 其推理速度在本地会更高一些)
+
 article: |
   Link to <a href='https://github.com/MoonInTheRiver/DiffSinger' style='color:blue;' target='_blank\'>Github REPO</a>
 example_inputs:

inference/svs/gradio/infer.py

@@ -77,7 +77,7 @@ class GradioInfer:
                              article=self.article,
                              examples=example_inputs,
                              enable_queue=True)
-        iface.launch(share=True,)# cache_examples=True)
+        iface.launch(share=True, cache_examples=True)
 
 
 if __name__ == '__main__':