Audio parameters for different Vocoder and TTS models #1254
Unanswered
arif334
asked this question in
General Q&A
Replies: 1 comment 2 replies
-
Audio parameters should match |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I've been training different models (from the recipe) with my
Bangla (Bengali)
dataset containing 12 hours of clean speech. So far, I've trainedGlowTTS
,Hifi-GAN
,MB-MelGAN
, andWaveRNN
. They are working fine with each other.But, then I trained
Tacotron2-DDC
andTacotron2-DCA
. They generate a somewhat good voice with the default GL vocoder but do not work with the trained neural vocoders (Hifi-GAN
,MB-MelGAN
). Combining Tacotron2 with the neural vocoders generates just noise.I've noticed some differences in the
audio
parameters of Tacotron2 and the other models.In Tacotron2 config, I've found these:
While in the other models, these values are as follows:
My question is, what should I do to be able to use Tacotron2 with other models? Should I retrain the Tacotron2 (and/or a vocoder) model with matching parameters? Changing those values to the trained model's config files (in either Tacotron2 or vocoder models) generates robotic (but intelligible) sound BTW.
Beta Was this translation helpful? Give feedback.
All reactions