search

syang1993 / gst-tacotron

A tensorflow implementation of the "Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis"
368 stars 110 forks source link

Path for Reference Audio #38

Open shrinidhin opened 4 years ago

shrinidhin commented 4 years ago

If I have to implement the second paper by setting the use_gst hyper parameter to false, where is the path for the reference audio for training to be provided?

syang1993 commented 4 years ago

Sorry for the late reply since I don't check the GitHub these days. If you don't want to use gst, the reference audio is the same with the target audio during training.