Open jinhonglu opened 3 years ago
Hello, no it is not.
Another question is that, is there any dev and test set, which I cat get access? Or I have to split the dev from the train myself?
No, you have to split it on your own.
I tried to use the alignment tool, and I realised each audio length is about 15-25s. Is it possible to modify the script to align shorter length(<10s)?
Hi, I just wonder whether the splitting you implemented is from one of the paper in the reference?