Update app.py

app.py

@@ -26,6 +26,7 @@ model = AutoModel(
     trust_remote_code=False,
     remote_code="./model.py",
     vad_model="fsmn-vad",
+    punc_model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch", 
     spk_model="cam++",
     vad_kwargs={"max_single_segment_time": 15000},
     ncpu=torch.get_num_threads(),
@@ -34,7 +35,7 @@ model = AutoModel(
     device=device,
 )
 
-def transcribe_audio(file_path, vad_model="fsmn-vad", spk_model="cam++", vad_kwargs='{"max_single_segment_time": 15000}', 
+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):
@@ -66,6 +67,7 @@ def transcribe_audio(file_path, vad_model="fsmn-vad", spk_model="cam++", vad_kwa
 inputs = [
     gr.Audio(type="filepath"),
     gr.Textbox(value="fsmn-vad", label="VAD Model"),
+    gr.Textbox(value="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch", label="PUNC Model"),
     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"),