v1.1.0

1. add vad model for sense voice to handle long audio file. the recognition result looks like :

2024-08-31 17:32:11,874 INFO [sense_voice.py:95] [13.24s - 15.19s] <|yue|><|EMO_UNKNOWN|><|BGM|><|woitn|>你而家打个电话暂时几啦
2024-08-31 17:32:11,979 INFO [sense_voice.py:95] [15.81s - 18.11s] <|yue|><|NEUTRAL|><|Speech|><|woitn|>姐 b一声之后留低口水
2024-08-31 17:32:12,037 INFO [sense_voice.py:95] [19.3s - 20.11s] <|en|><|NEUTRAL|><|Speech|><|woitn|>mary
2024-08-31 17:32:12,093 INFO [sense_voice.py:95] [20.39s - 21.2s] <|en|><|EMO_UNKNOWN|><|Speech|><|woitn|>sorry
2024-08-31 17:32:12,166 INFO [sense_voice.py:95] [22.44s - 23.7s] <|yue|><|EMO_UNKNOWN|><|Speech|><|woitn|>我拣咗做好人噶
2024-08-31 17:32:12,252 INFO [sense_voice.py:95] [24.69s - 26.35s] <|yue|><|NEUTRAL|><|Speech|><|woitn|>我而家就去见陈永仁
2024-08-31 17:32:12,384 INFO [sense_voice.py:95] [26.92s - 29.65s] <|yue|><|NEUTRAL|><|Speech|><|woitn|>无论点都好啦我会俾一个身份佢

...

Release V1.0.0

1. Add CLI for sensevoice onnx