Kyubyong Park

Okay, let me give you an example. Correct me if I'm wrong. Assume a value of an element of the original magnitude is 2. The best model should output 2,...

Actually, I've changed the relevant codes. See https://github.com/Kyubyong/tacotron/blob/master/utils.py#L42 and https://github.com/Kyubyong/tacotron/blob/master/eval.py#L65 I think this revision is closer to the paper. Thanks, guys!

Would you share your code?

Absolutely. I'm doing that for 10 non-English languages. So far so good.

If you see Table 1 on page 4 of the paper, the second layer of the Conv1D projections is described as `conv-3-128-Linear`. If we don't apply activation, we shouldn't normalize,...

@candlewill Thanks for your question. Well, what I meant was we shouldnt apply activation or normalization before the final layer because usually we are to yield logits. In this case,...

The fatc that 3/5 of the generated file is silent looks fine, because we intended to reconstruct them (zero paddings). The training curve looks good, too. When I was training...

Some human-like voice is heard, though I can't recognize what he(?)'s saying about. (I think it's natural because the data is far from enough) I've recently revised the code. When...

@xuerq I'm running a sanity-check test. I'll share with you as soon as it's done.

Can you share your training loss graph?