Update app.py

app.py

@@ -225,7 +225,7 @@ def transcribe(audio, spk):
     y /= np.max(np.abs(y))
 
     spk_emb = np.zeros((82,))
-    spk_emb[spk-1] = 1
+    spk_emb[int(spk)-1] = 1
     
     mel_sp, mel_cep = create_mel(y)
     sp = create_sp(mel_cep, spk_emb)
@@ -239,7 +239,7 @@ demo = gr.Interface(
     transcribe,
     [
         gr.Audio(),
-        gr.Slider(1, 82, value=21, label="Count", info="Choose between 1 and 82")
+        gr.Slider(1, 82, value=21, label="Count", step=1, info="Choose between 1 and 82")
     ],
     "audio",
 )