Simon-chai

## 🚀 Feature When we use get_speech_timestamps function we can assgin Parameters like _min_speech_duration_ms_,as I see it, they two actually are doing the same thing,does it mean that VADIterator can...

Chinese to chinese(traditional) translate output funny result

3

 See the pic. Look like kind of chinese -> english -> chinese(tranditional) result.Is multilanguage translation implement by this way? And more important,the result is not chinese(tranditional)，both input and output...

## 🐛 Bug 使用pipeline进行ASR时，当输入是scp文件，ASR结束后进程不解除输出目录的文件占用 ### To Reproduce 运行以下代码 ``` from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks import shutil inference_pipeline = pipeline( task=Tasks.auto_speech_recognition, model='iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch', model_revision="v2.0.4") scp = 'path/to/your/scp/0.scp' inference_pipeline(input=scp, output_dir='./output_dir')...