Yeongtae
@IvanKobzarev Although I use 1.3.0 to convert my customized model, I have seen the same error message on the android studio.   Are there any unsupported layers or data...
> @IvanKobzarev > Although I use 1.3.0 to convert my customized model, > I have seen the same error message on the android studio. > >  >  >...
Skip it using try catch. It will be temporary solution.
Train more steps. The parameter 'output per step' affects the quality of Tacotron model. Reduce 'embedding_dim', it makes converging model more fast. But its lose many language information.
@m-toman Could you tell me the number of generated samples per sec of your wavernn model. In addition, your GPU device. In my case with my forked branch from your...
@m-toman nvidia-tacotron2 and nvidia-waveglow are well optimized. In my experment, a v100 machine can generate 160k samples/sec, 350k samples/sec each. But waveglow have a problem about reverb. I'm trying to...
So I'm using 8 v100 gpus to train waveglow.
@m-toman do you make some results with this repository? Could you share a sample audio?
Good. It looks like using operation optimization technique to reduce matrix multiplication.