LiveSpeechPortraits icon indicating copy to clipboard operation
LiveSpeechPortraits copied to clipboard

More details about the clip separation for training

Open DreamtaleCore opened this issue 2 years ago • 2 comments

Hi, Recently I'm trying to repeat the training part of audio2feature, could u please share more details about the dataset construction, e.g., the duration of each clip, and the overlap of two clips?

Thanks and looking for your reply😊.

Yunfei

DreamtaleCore avatar Apr 06 '22 07:04 DreamtaleCore

There're no overlaps between the two clips. I just use one clip for training. Check issue #27.

YuanxunLu avatar Apr 06 '22 10:04 YuanxunLu

Thanks! This helps me a lot.

DreamtaleCore avatar Apr 08 '22 07:04 DreamtaleCore