Updates about WebRTCVad
change of the usage
initial：python audiosplit.py <aggressiveness> <dir to result>
now:python audiosplit.py <padding duration> <path to wav file/directory> <path to result>two modes
Support splitting a single audio or all the audios in a certain file. The latter one is for re-splitting the audios which are longer than 30 seconds.To see more details, click here
Updates about Xunfeisdk
Since tuning the parameter needs more labelled dataset, Zhaoqing and I think maybe Xunfei can help us get rid of the onerous work of manually labelling the audios. So I simplify the code to make it more easier to use.
C code to Python
The example code that Xunfei offer is written by C. But it is so complicated in string operations. So I change the code into Python.delete punctuation
To see more details and complete usage, click (here)[https://liuziyi219.github.io/2019/07/06/Chinese-Pipeline-How-to-use-XunfeiSDK/]