Closed longjoke closed 2 years ago
currently ground truth
Do you think it could be advantageous to use Tacotron2 output? Since Fastpitch is trained on that. It should be fairly easy to do using the extract-mels.py from Fastpitch with the --extract-mels-teacher argument.
Potentially, or even the FastPitch ones perhaps. I plan to experiment with this soon, once FastPitch gets its next update
Are the HiFi-GAN models trained using mel-spectrograms generated from the ground truth audio, from the Tacotron2 models or from the Fastpitch models?