Update app.py

app.py

@@ -52,13 +52,13 @@ try:
         global n_spk, tgt_sr, net_g, vc, cpt, version
         if sid == "" or sid == []:
             global hubert_model
-            if hubert_model != None:  # 考虑到轮询, 需要加个判断看是否 sid 是由有模型切换到无模型的
+            if hubert_model != None:  # Considering polling, we need to add a check to see if the sid is switched from a model to a model-free state.
                 print("clean_empty_cache")
                 del net_g, n_spk, vc, hubert_model, tgt_sr  # ,cpt
                 hubert_model = net_g = n_spk = vc = hubert_model = tgt_sr = None
                 if torch.cuda.is_available():
                     torch.cuda.empty_cache()
-                ###楼下不这么折腾清理不干净
+                ###The downstairs won't be clean without this much trouble
                 if_f0 = cpt.get("f0", 1)
                 version = cpt.get("version", "v1")
                 if version == "v1":
@@ -166,7 +166,7 @@ try:
                 )
                 if file_index != ""
                 else file_index2
-            )  # 防止小白写错，自动帮他替换掉
+            )  # Prevent newbies from making mistakes and automatically replace them for them
             # file_big_npy = (
             #     file_big_npy.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
             # )
@@ -213,19 +213,19 @@ try:
     app = gr.Blocks()
     with app:
         with gr.Tabs():
-            with gr.TabItem("在线demo"):
+            with gr.TabItem("Online demo"):
                 gr.Markdown(
                     value="""
-                    RVC 在线demo
+                    RVC Online demo
                     """
                 )
-                sid = gr.Dropdown(label=i18n("推理音色"), choices=sorted(names))
+                sid = gr.Dropdown(label=i18n("Mystery Tone"), choices=sorted(names))
                 with gr.Column():
                     spk_item = gr.Slider(
                         minimum=0,
                         maximum=2333,
                         step=1,
-                        label=i18n("请选择说话人id"),
+                        label=i18n("Please select the speaker id"),
                         value=0,
                         visible=False,
                         interactive=True,
@@ -236,12 +236,12 @@ try:
                     outputs=[spk_item],
                 )
                 gr.Markdown(
-                    value=i18n("男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ")
+                    value=i18n("For male to female, +12key is recommended, for female to male, -12key is recommended. If the sound range explodes and causes timbre distortion, you can adjust it to the appropriate range yourself.")
                 )
-                vc_input3 = gr.Audio(label="上传音频（长度小于90秒）")
-                vc_transform0 = gr.Number(label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0)
+                vc_input3 = gr.Audio(label="Upload audio (less than 90 seconds in length)")
+                vc_transform0 = gr.Number(label=i18n("Transpose(integer, number of semitones, octave up 12 octave down -12)"), value=0)
                 f0method0 = gr.Radio(
-                    label=i18n("选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU"),
+                    label=i18n("Select the pitch extraction algorithm. You can use pm to speed up the input singing voice. Harvest has good bass but is extremely slow. Crepe has good effect but consumes GPU."),
                     choices=["pm", "harvest", "crepe"],
                     value="pm",
                     interactive=True,
@@ -249,34 +249,34 @@ try:
                 filter_radius0 = gr.Slider(
                     minimum=0,
                     maximum=7,
-                    label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
+                    label=i18n(">=3, use median filtering on the result of harvest pitch recognition, the value is the filter radius, which can reduce mute"),
                     value=3,
                     step=1,
                     interactive=True,
                 )
                 with gr.Column():
                     file_index1 = gr.Textbox(
-                        label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+                        label=i18n("Feature retrieval library file path, if empty, use the drop-down selection result"),
                         value="",
                         interactive=False,
                         visible=False,
                     )
                 file_index2 = gr.Dropdown(
-                    label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+                    label=i18n("Automatically detect index path, drop-down selection"),
                     choices=sorted(index_paths),
                     interactive=True,
                 )
                 index_rate1 = gr.Slider(
                     minimum=0,
                     maximum=1,
-                    label=i18n("检索特征占比"),
+                    label=i18n("Search feature proportion"),
                     value=0.88,
                     interactive=True,
                 )
                 resample_sr0 = gr.Slider(
                     minimum=0,
                     maximum=48000,
-                    label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+                    label=i18n("Post-processing resampling to the final sampling rate, 0 means no resampling"),
                     value=0,
                     step=1,
                     interactive=True,
@@ -284,22 +284,22 @@ try:
                 rms_mix_rate0 = gr.Slider(
                     minimum=0,
                     maximum=1,
-                    label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
+                    label=i18n("The input source volume envelope replaces the output volume envelope blending ratio. The closer it is to 1, the more the output envelope is used."),
                     value=1,
                     interactive=True,
                 )
                 protect0 = gr.Slider(
                     minimum=0,
                     maximum=0.5,
-                    label=i18n("保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"),
+                    label=i18n("Protects clear consonants and breathing sounds, and prevents electronic music tearing and other artifacts. It is not enabled when it is set to 0.5. It is more effective when it is lowered, but the indexing effect may be reduced."),
                     value=0.33,
                     step=0.01,
                     interactive=True,
                 )
-                f0_file = gr.File(label=i18n("F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调"))
-                but0 = gr.Button(i18n("转换"), variant="primary")
-                vc_output1 = gr.Textbox(label=i18n("输出信息"))
-                vc_output2 = gr.Audio(label=i18n("输出音频(右下角三个点,点了可以下载)"))
+                f0_file = gr.File(label=i18n("F0 curve file, optional, one line per pitch, replaces the default F0 and sharp and flat tones"))
+                but0 = gr.Button(i18n("Convert"), variant="primary")
+                vc_output1 = gr.Textbox(label=i18n("Output information"))
+                vc_output2 = gr.Audio(label=i18n("Output audio (three dots in the lower right corner, click to download)"))
                 but0.click(
                     vc_single,
                     [