Update app.py

app.py

@@ -18,7 +18,7 @@ speaker_embeddings = {
 }
 
 
-def predict(text, audio, speaker):
+def predict(text, speaker):
     if len(text.strip()) == 0:
         return (16000, np.zeros(0).astype(np.int16))
 
@@ -101,7 +101,7 @@ gr.Interface(
     fn=predict,
     inputs=[
         gr.Text(label="Input Text"),
-        gr.Audio(label="Input Speech", type="numpy"),
+        # gr.Audio(label="Input Speech", type="numpy"),
         gr.Radio(label="Speaker", choices=[
             "BDL (male)",
             "CLB (female)",
@@ -109,7 +109,8 @@ gr.Interface(
             "RMS (male)",
             "SLT (female)",
             "Surprise Me!"
-        ]),
+        ],
+        value="BDL (male)"),
     ],
     outputs=[
         gr.Audio(label="Generated Speech", type="numpy"),