Phu-Thien Nguyen

Thank for replying. I'm working with Tensorflow Tacotron-2. My model synthesizes good results. Now I want to apply parallel Wavenet to speed up it. I have to read, understand your...

Sorry for bothering you, @zhf459 but Could you post some output samples of Clari (or Parallel) wavenet model, please? I've checked other's results, but they are so bad. How is...

what do you mean when saying "not good enough" sir? The model training speed, synthesizing speed, or it is about the predicting performance? Thank you sir, for your efforts

1. Should the sources always end with a period, ie one sentence, one audio file? - yes, you should, because there are some silence at begining and end of sound...

My Tacotron model results human (noisy) voice at step ~2,000th. quite clear at 20,000th [Tacotron_results.zip](https://github.com/Rayhane-mamah/Tacotron-2/files/2381540/Tacotron_results.zip) I dont know but I think it depends on your data.

You might be calling an argument named 'fftsize' which does not exist. (I think it is a param of a class or function) trace your error logs, find it and...

You have made some changes in hparams. Do you think that is the reason? Have you ever tried using as default?

all above answers was wrong, at least they are wrong because the answerers posted without any explaination. keep `http_demo = true`, this is needed if you want to config streams...