Closed BridgetteSong closed 2 years ago
I found author committed codes as following, but i don't understand: "Saves on the MDense/softmax computation since we only need to compute 8 values instead of 256." https://github.com/mozilla/LPCNet/commit/d24f49e346b85b5cb2c89c6dadcc913ce004fe83
understand now
@BridgetteSong I'm really sorry to bothering you, but could you explain about "Representing output pdf as binary probability tree" commit?
I apply this commit, but synthesis speech quality is not good. (Synthesis speed is slightly improved.)
Using softmax and sample_from_pdf() instead of sample_mdense(), synthesis speech quality is good.
Do you have any idea?
@BridgetteSong I'm really sorry to bothering you, but could you explain about "Representing output pdf as binary probability tree" commit?
I apply this commit, but synthesis speech quality is not good. (Synthesis speed is slightly improved.)
Using softmax and sample_from_pdf() instead of sample_mdense(), synthesis speech quality is good.
Do you have any idea?
Why use sigmoid activation not softmax activation? if I don't use end2end flag, loss function is _sparse_categoricalcrossentropy, and don't use _fromlogits=True, so _y_pred_ will not encode a probability distribution.