Hi,
I listened the case your shared, very expressive. Can you share your models and configurations? I want to train a model using your configurations recently, and take the model as reference.
Thanks very much
Hi
can share your test waves? are they like https://waveflow-demo.github.io/?
another question, Is there any server synthesizer?
Do you compare of time of synthesizing with tacatron (like Mozilla)? Is it faster?
best regards.
It seems that the shift_1d is called to guarantee the causality on the height dimension. But the receptive field of the following Wavenet2D module is greater than 3 (8 layers, each has kernel size of 3). Then how dose the shift_1d function which only shifts the tensor on height dimension by one unit guarantee the causality?