New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

while fine_tuning is True during training quantizer, what has to be base_mel_path as input? #8

Open

ghost opened this issue Aug 9, 2023 · 0 comments

ghost commented Aug 9, 2023 •

edited by ghost

Loading

MQTTS/quantizer/meldataset.py

Line 153 in be5c48f

    
           os.path.join(self.base_mels_path, os.path.splitext(os.path.split(filename)[-1])[0] + '.npy'))

by default, it's none in train.py

also, the do_0000xxx checkpoint saved during training the quantizer, I would like to know where it is used, if used in training the 100M VQTTS

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment