Merge pull request #147 from limbang/4.0

fix: #140，添加 edge-tts 生成时男性女性选择

webUI.py

@@ -99,11 +99,12 @@ def vc_fn(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise
         raise gr.Error(e)
 
 
-def tts_func(_text,_rate):
+def tts_func(_text,_rate,_voice):
     #使用edge-tts把文字转成音频
     # voice = "zh-CN-XiaoyiNeural"#女性，较高音
     # voice = "zh-CN-YunxiNeural"#男性
     voice = "zh-CN-YunxiNeural"#男性
+    if ( _voice == "女" ) : voice = "zh-CN-XiaoyiNeural"
     output_file = _text[0:10]+".wav"
     # communicate = edge_tts.Communicate(_text, voice)
     # await communicate.save(output_file)
@@ -112,11 +113,11 @@ def tts_func(_text,_rate):
     elif _rate<0:
         ratestr="{:.0%}".format(_rate)#减号自带
 
-    p=subprocess.Popen(["edge-tts",
-                        "--text",_text,
-                        "--write-media",output_file,
-                        "--voice",voice,
-                        "--rate="+ratestr]
+    p=subprocess.Popen("edge-tts "+
+                        " --text "+_text+
+                        " --write-media "+output_file+
+                        " --voice "+voice+
+                        " --rate="+ratestr
                         ,shell=True,
                         stdout=subprocess.PIPE,
                         stdin=subprocess.PIPE)
@@ -124,9 +125,9 @@ def tts_func(_text,_rate):
     return output_file
 
 
-def vc_fn2(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,text2tts,tts_rate,F0_mean_pooling,enhancer_adaptive_key):
+def vc_fn2(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,text2tts,tts_rate,tts_voice,F0_mean_pooling,enhancer_adaptive_key):
     #使用edge-tts把文字转成音频
-    output_file=tts_func(text2tts,tts_rate)
+    output_file=tts_func(text2tts,tts_rate,tts_voice)
 
     #调整采样率
     sr2=44100
@@ -206,6 +207,7 @@ with gr.Blocks(
                 with gr.TabItem("文字转音频"):
                     text2tts=gr.Textbox(label="在此输入要转译的文字。注意，使用该功能建议打开F0预测，不然会很怪")
                     tts_rate = gr.Number(label="tts语速", value=0)
+                    tts_voice = gr.Radio(label="性别",choices=["男","女"], value="男")
                     vc_submit2 = gr.Button("文字转换", variant="primary")
             with gr.Row():
                 with gr.Column():
@@ -221,6 +223,7 @@ with gr.Blocks(
         vc_submit.click(vc_fn, [sid, vc_input3, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,F0_mean_pooling,enhancer_adaptive_key], [vc_output1, vc_output2])
         vc_submit2.click(vc_fn2, [sid, vc_input3, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,text2tts,tts_rate,F0_mean_pooling,enhancer_adaptive_key], [vc_output1, vc_output2])
         debug_button.change(debug_change,[],[])
+        vc_submit2.click(vc_fn2, [sid, vc_input3, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,text2tts,tts_rate,tts_voice,F0_mean_pooling,enhancer_adaptive_key], [vc_output1, vc_output2])
         model_load_button.click(modelAnalysis,[model_path,config_path,cluster_model_path,device,enhance],[sid,sid_output])
         model_unload_button.click(modelUnload,[],[sid,sid_output])
     app.launch()