update

app_locally.py

@@ -14,7 +14,8 @@ ckpt_converter = 'checkpoints/converter'
 tone_color_converter = ToneColorConverter(f'{ckpt_converter}/config.json', device=device)
 tone_color_converter.load_ckpt(f'{ckpt_converter}/checkpoint.pth')
 
-def predict(prompt, style, audio_file_pth, mic_file_path, use_mic, language):
+#def predict(prompt, style, audio_file_pth, mic_file_path, use_mic, language):
+def predict(prompt, audio_file_pth, mic_file_path, use_mic, language):
     # initialize a empty info
     text_hint = ''
 
@@ -70,7 +71,8 @@ def predict(prompt, style, audio_file_pth, mic_file_path, use_mic, language):
 
     speed = 1.0
 
-    tts_model.tts_to_file(prompt, speaker_id, src_path, speaker=style, language=language)
+    #tts_model.tts_to_file(prompt, speaker_id, src_path, speaker=style, language=language)
+    tts_model.tts_to_file(prompt, speaker_id, src_path, language=language)
 
     save_path = f'{output_dir}/output.wav'
     # Run the tone color converter
@@ -129,13 +131,13 @@ with gr.Blocks(analytics_enabled=False) as demo:
                 info="One or two sentences at a time is better. Up to 200 text characters.",
                 value="He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.",
             )
-            style_gr = gr.Dropdown(
-                label="Style",
-                info="Select a style of output audio for the synthesised speech. (Chinese only support 'default' now)",
-                choices=['default', 'whispering', 'cheerful', 'terrified', 'angry', 'sad', 'friendly'],
-                max_choices=1,
-                value="default",
-            )
+            #style_gr = gr.Dropdown(
+            #    label="Style",
+            #    info="Select a style of output audio for the synthesised speech. (Chinese only support 'default' now)",
+            #    choices=['default', 'whispering', 'cheerful', 'terrified', 'angry', 'sad', 'friendly'],
+            #    max_choices=1,
+            #    value="default",
+            #)
             ref_gr = gr.Audio(
                 label="Reference Audio",
                 info="Click on the ✎ button to upload your own target speaker audio",
@@ -165,11 +167,13 @@ with gr.Blocks(analytics_enabled=False) as demo:
 
             gr.Examples(examples,
                         label="Examples",
-                        inputs=[input_text_gr, style_gr, ref_gr, mic_gr, use_mic_gr, language],
+                        #inputs=[input_text_gr, style_gr, ref_gr, mic_gr, use_mic_gr, language],
+                        inputs=[input_text_gr, ref_gr, mic_gr, use_mic_gr, language],
                         outputs=[out_text_gr, audio_gr, ref_audio_gr],
                         fn=predict,
                         cache_examples=False,)
-            tts_button.click(predict, [input_text_gr, style_gr, ref_gr, mic_gr, use_mic_gr, language], outputs=[out_text_gr, audio_gr, ref_audio_gr])
+            #tts_button.click(predict, [input_text_gr, style_gr, ref_gr, mic_gr, use_mic_gr, language], outputs=[out_text_gr, audio_gr, ref_audio_gr])
+            tts_button.click(predict, [input_text_gr, ref_gr, mic_gr, use_mic_gr, language], outputs=[out_text_gr, audio_gr, ref_audio_gr])
 
 demo.queue()  
 demo.launch(debug=True, show_api=True)