search

keithito / tacotron

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
MIT License
2.95k stars 959 forks source link

Using pre-trained model for new speaker? #224

Open xerdink opened 6 years ago

xerdink commented 6 years ago

Hi, thanks for great work.

I am trying to use pre-trained model for new speaker. Do you suggest any guide? Or train from scratch?