Open mrgloom opened 5 years ago
https://github.com/Rayhane-mamah/Tacotron-2/issues/29#issuecomment-465932878
It's 'ground-truth-aligned'. Meaning the state of the network follows the ground truth, 'real' spectrogram's timing. Yielding a predicted spectrogram that is the same length of hops as the real spectrogram. This is useful if you want to then train the Wavenet with generated specs rather than 'real' specs.
This issue should be closed, since the question has been answered.
What is GTA?