how to run the final Step to create speaker audio utterance?

[dimuthuanuraj]

Dear @t68i663 @cmots @LewiVir ,

I am willing to use your pipeline to create a database for Sri Lankan local languages. I run your run_single.py and run.py both and got the text file that contains the starting time & duration of the utterance.

But, I could not able to figure it out what is the next step.
how to cut the video according to that txt file and obtaining the final outcome.?
Also how to do the data cleaning?

Could you please help me? I hope you will able to find some time to show me the path and answer my question.

Thank you.
Anuraj