wavenet_vocoder icon indicating copy to clipboard operation
wavenet_vocoder copied to clipboard

Published 20 hours ago • verified publisher icon r9y9

Slow Inference

Open luantunez opened this issue 3 years ago • 1 comments

Hello and thank you for sharing your work! I am encountering the problem of the inference time for your model being quite slow in the colab you shared. Could you explain why? Is there any workarround? I have seen you recommended ParallelWaveGan on issue #208 but I would really like to use your repository models and results. Thank you very much in advance!

luantunez avatar Jul 14 '21 13:07 luantunez

Also, what are the npy files in "tacotron_output/eval/", like "tacotron_output/eval/speech-mel-00001.npy" ? How can I create these to perform new inferences? Thank you again!

luantunez avatar Jul 14 '21 13:07 luantunez