NTT123/vietTTS

mfa version

MostafaAlaviyan opened this issue · 2 comments

hi
I want to train fastspeech2 on a Persian dataset with durations extracted from MFA. which version of mfa do U use for training? do you have any preprocessing on your datasets?

You can install MFA via pip: https://montreal-forced-aligner.readthedocs.io/en/latest/installation.html
I don't think version of MFA is affected in this situation.
preprocessing data of him is here: https://colab.research.google.com/gist/NTT123/c99b5a391af56e0cb8f7b190d3d7f0ee/infore-mfa-example.ipynb

Closed due to inactivity.