voice_activity_detection icon indicating copy to clipboard operation
voice_activity_detection copied to clipboard

Published 20 hours ago • verified publisher icon filippogiruzzi

Does anyone know how to train the model with my own dataset?

Open vayala opened this issue 4 years ago • 2 comments

I have been trying to train the model with a new dataset that contains .WAV but it requires me to use the model that was used for .FLAC. Thus, I have been wondering how can I do this?

vayala avatar May 12 '20 20:05 vayala

hi, have you trained the model with your dataset successfully?

Reckless564 avatar Jul 17 '20 13:07 Reckless564

Just use Sox or pysox to convert

StuartIanNaylor avatar Jan 22 '21 20:01 StuartIanNaylor