Open mutiann opened 5 years ago
In my training with my own data the loss converges rapidly, though as well as the alignments. After merely 1000 steps the attention part produce ~0.9 score for the last step of encoder outputs in most cases, and during synthesis (with Griffim-Lim) the Tacotron model would produce similar alignments and human-like garbling completely irrelevant with input text. Anyone have ideas about that? Thanks.
@dy-octa Hi, have you solved this problem?