How to fine tune a new voice using pretrained model about mellotron HOT 3 OPEN

Hi @rafaelvalle can you please answer to the questions on this issue?
I'm having similar problems and can't achieve the quality as on the papers.

from mellotron.

1. Either way should work.
2. The defaults should be a good start. You might need to adjust F0_min to match the lowest F0 of your speaker.
3. Train until the validation loss stops decreasing.

Let us know if you have specific issues.

from mellotron.

@rafaelvalle , I trained a new speaker with 17mins of speaking data.
After 9k iterations it generated a good alignment then used the best alignment checkpoint to test speaking style transfer.
The style transfer was 100% perfect and can understand the words spoken by the trained speaker but the voice was a little croaky . The audio recordings of the trained speaker was not croaky voice.

Which of the training params in hparams.py can I tune to get rid of the croaky voice so the voice is much smoother like the trained speaker voice.

Shall I also adjust the F0_min to higher or lower? any other params to adjust?

I'm also thinking maybe I should increase the voice data from 17mins to 25mins and and re-train the speaker?

from mellotron.