Open zyj008 opened 6 years ago
if it can help, i used the default hparams with ljspeech 1.1 and the training started to produce intelligible sound on 18k step
I'd recommend to restart training but i'm not sure, since it seems there is some randomization that might shift convergence
Hi! Thanks for your contribution! I have trained the model on LJSpeech dataset with your codes. But I found the loss is not converge with your default hparams. Here are some results on tensorboard. Could you give me some advice?
batch_size=32 lr=0.002
batch_size=32 lr=0.001
batch_size=64 lr=0.001
batch_size =64 lr=0.0006
batch_size=32 lr=0.0001
batch_size=32 lr=0.00002
Finally, the model seems converge. But the alignment is not good. The step-51000-align.png is like this. Should I keep on training or kill this process and try other hparams? Can you give me some advice?