Update app.py

app.py

@@ -38,7 +38,7 @@ model = AutoModel(
     device=device,
 )
 
-def transcribe_audio(file_path, vad_model="fsmn-vad", punc_model="ct-punc", vad_kwargs='{"max_single_segment_time": 30000}', 
+def transcribe_audio(file_path, vad_model="fsmn-vad", punc_model="ct-punc", spk_model="cam++", vad_kwargs='{"max_single_segment_time": 15000}', 
                      batch_size=1, language="auto", use_itn=True, batch_size_s=60, 
                      merge_vad=True, merge_length_s=15, batch_size_threshold_s=50, 
                      hotword=" ", ban_emo_unk=True):
@@ -57,7 +57,6 @@ def transcribe_audio(file_path, vad_model="fsmn-vad", punc_model="ct-punc", vad_
             merge_length_s=merge_length_s,
             batch_size_threshold_s=batch_size_threshold_s,
             hotword=hotword,
-            spk_model=spk_model,
             ban_emo_unk=ban_emo_unk
         )
 
@@ -72,7 +71,8 @@ inputs = [
     gr.Audio(type="filepath"),
     gr.Textbox(value="fsmn-vad", label="VAD Model"),
     gr.Textbox(value="ct-punc", label="PUNC Model"),
-    gr.Textbox(value='{"max_single_segment_time": 30000}', label="VAD Kwargs"),
+    gr.Textbox(value="cam++", label="SPK Model"),
+    gr.Textbox(value='{"max_single_segment_time": 15000}', label="VAD Kwargs"),
     gr.Slider(1, 10, value=1, step=1, label="Batch Size"),
     gr.Textbox(value="auto", label="Language"),
     gr.Checkbox(value=True, label="Use ITN"),