deep-voice-conversion icon indicating copy to clipboard operation
deep-voice-conversion copied to clipboard

Published 20 hours ago • verified publisher icon andabi

run train2 stop at Model loaded

Open guanjian729 opened this issue 6 years ago • 1 comments

hello, i use trained weights from #28 ,@VictoriaBentell. and run python eval1.py timit is ok. 121 but in next step,python train2.py timit arctic/slt,I find the training stop at (Model loaded. mode: train2, model_name: epoch_12_step_6924) 333 who can tall me why? thanks. environment:Ubuntu16.04 tf-gpu:1.4.0

guanjian729 avatar May 04 '18 06:05 guanjian729

Check paths, there is some inconsistency in using *.WAV & *.wav in settings and hparams.py. Also might be worth disabling 'queue' mode in code, there are some bugs there.

Techmind avatar May 04 '18 09:05 Techmind