Update infer.py

infer.py

@@ -643,7 +643,7 @@ with gr.Blocks() as app:
             visible=False,
             interactive=True,
         )
-        refresh_model = gr.Button("(1)Refresh model list", variant="primary")
+        refresh_model = gr.Button("Refresh model list", variant="primary")
         clean_button = gr.Button("Clear Model from memory", variant="primary")
         refresh_model.click(
             fn=check_models, inputs=[], outputs=[sid, file_index]
@@ -653,26 +653,26 @@ with gr.Blocks() as app:
         selected_model = gr.Markdown(value="# <center> No model selected")
         with gr.Row():
             with gr.Column():
-                vc_audio_mode = gr.Dropdown(label="Input voice", choices=["Youtube", "Input path", "Upload audio", "TTS Audio"], allow_custom_value=False, value="Youtube")
-                # Youtube
-                vc_download_audio = gr.Dropdown(label="Provider", choices=["Youtube"], allow_custom_value=False, visible=True, value="Youtube", info="Select provider (Default: Youtube)")
-                vc_link = gr.Textbox(label="Youtube URL", visible=True, info="Example: https://www.youtube.com/watch?v=Nc0sB1Bmf-A", placeholder="https://www.youtube.com/watch?v=...")
-                vc_log_yt = gr.Textbox(label="Output Information", visible=True, interactive=False)
-                vc_download_button = gr.Button("(2)Download Audio", variant="primary", visible=True)
-                vc_audio_preview = gr.Audio(label="Downloaded Audio Preview", visible=True)
+                vc_audio_mode = gr.Dropdown(label="Input voice", choices=["Input path", "Upload audio", "Youtube", "TTS Audio"], allow_custom_value=False, value="Upload audio")
                 # Input
                 vc_input = gr.Textbox(label="Input audio path", visible=False)
                 # Upload
-                vc_microphone_mode = gr.Checkbox(label="Use Microphone", value=False, visible=False, interactive=True)
-                vc_upload = gr.Audio(label="Upload audio file", source="upload", visible=False, interactive=True)
+                vc_microphone_mode = gr.Checkbox(label="Use Microphone", value=False, visible=True, interactive=True)
+                vc_upload = gr.Audio(label="Upload audio file", source="upload", visible=True, interactive=True)
+                # Youtube
+                vc_download_audio = gr.Dropdown(label="Provider", choices=["Youtube"], allow_custom_value=False, visible=False, value="Youtube", info="Select provider (Default: Youtube)")
+                vc_link = gr.Textbox(label="Youtube URL", visible=False, info="Example: https://www.youtube.com/watch?v=Nc0sB1Bmf-A", placeholder="https://www.youtube.com/watch?v=...")
+                vc_log_yt = gr.Textbox(label="Output Information", visible=False, interactive=False)
+                vc_download_button = gr.Button("Download Audio", variant="primary", visible=False)
+                vc_audio_preview = gr.Audio(label="Downloaded Audio Preview", visible=False)
                 # TTS
                 tts_text = gr.Textbox(label="TTS text", info="Text to speech input", visible=False)
                 tts_voice = gr.Dropdown(label="Edge-tts speaker", choices=voices, visible=False, allow_custom_value=False, value="en-US-AnaNeural-Female")
                 # Splitter
                 vc_split_model = gr.Dropdown(label="Splitter Model", choices=["hdemucs_mmi", "htdemucs", "htdemucs_ft", "mdx", "mdx_q", "mdx_extra_q"], allow_custom_value=False, visible=True, value="htdemucs", info="Select the splitter model (Default: htdemucs)")
                 vc_split_log = gr.Textbox(label="Output Information", visible=True, interactive=False)
-                vc_split_yt = gr.Button("(3)Split Audio", variant="primary", visible=False)
-                vc_split = gr.Button("(3)Split Audio", variant="primary", visible=True)
+                vc_split_yt = gr.Button("Split Audio", variant="primary", visible=False)
+                vc_split = gr.Button("Split Audio", variant="primary", visible=True)
                 vc_vocal_preview = gr.Audio(label="Vocal Preview", interactive=False, visible=True)
                 vc_inst_preview = gr.Audio(label="Instrumental Preview", interactive=False, visible=True)
             with gr.Column():
@@ -685,7 +685,7 @@ with gr.Blocks() as app:
                     label="Pitch extraction algorithm",
                     info=f0method_info,
                     choices=f0method_mode,
-                    value="crepe",
+                    value="pm",
                     interactive=True,
                 )
                 index_rate0 = gr.Slider(
@@ -737,7 +737,7 @@ with gr.Blocks() as app:
             with gr.Column():
                 vc_log = gr.Textbox(label="Output Information", interactive=False)
                 vc_output = gr.Audio(label="Output Audio", interactive=False)
-                vc_convert = gr.Button("(4)Convert", variant="primary")
+                vc_convert = gr.Button("Convert", variant="primary")
                 vc_vocal_volume = gr.Slider(
                     minimum=0,
                     maximum=10,
@@ -759,7 +759,7 @@ with gr.Blocks() as app:
                     visible=True
                 )
                 vc_combined_output = gr.Audio(label="Output Combined Audio", visible=True)
-                vc_combine =  gr.Button("(5)Combine",variant="primary", visible=True)
+                vc_combine =  gr.Button("Combine",variant="primary", visible=True)
         vc_convert.click(
             vc_single,
             [