Update app.py

app.py

@@ -52,7 +52,7 @@ hubert = torch.hub.load("bshall/hubert:main", "hubert_soft")
 
 _ = utils.load_checkpoint("G_18000.pth", net_g_ms, None)
 
-def vc_fn(input_audio,vc_transform,vc_input4):
+def vc_fn(input_audio,vc_transform,vcid):
     if input_audio is None:
         return "You need to upload an audio", None
     sampling_rate, audio = input_audio
@@ -77,7 +77,7 @@ def vc_fn(input_audio,vc_transform,vc_input4):
         print(sampling_rate)
         f0 = resize2d(f0, len(soft[:, 0])) * vc_transform
         soft[:, 0] = f0 / 10
-    sid = torch.LongTensor([vc_input4])
+    sid = torch.LongTensor([vcid])
     stn_tst = torch.FloatTensor(soft)
     with torch.no_grad():
         x_tst = stn_tst.unsqueeze(0)
@@ -95,10 +95,10 @@ with app:
         with gr.TabItem("Basic"):
             vc_input3 = gr.Audio(label="Input Audio (30s limitation)")
             vc_transform = gr.Number(label="transform",value=1.0)
-            vc_input4=gr.Textbox(label="speakerID",value=0),
+            vcid=gr.Textbox(label="speakerID",value=0),
             vc_submit = gr.Button("Convert", variant="primary")
             vc_output1 = gr.Textbox(label="Output Message")
             vc_output2 = gr.Audio(label="Output Audio")
-        vc_submit.click(vc_fn, [vc_input3, vc_transform, vc_input4], [vc_output1, vc_output2])
+        vc_submit.click(vc_fn, inputs=vcid, [vc_input3, vc_transform,], [vc_output1, vc_output2])
 
     app.launch()