Generated outputs sound robotic in some cases!

[aniketp02]

Hello!

I have trained GradTTS on quite a few datasets and observed that it produces excellent results on most of the voices, but the generated results on heavy voices sound very robotic! Can anyone explain any possible reasons for this?

I have attached the samples of original and generated voices.

Thank you!

• Original male voice

org_sagar.mov

• Generated male voice

gen_sagar.mov

• Original female voice

org_anupama.mov

• Generated female voice

gen_anupama.mov

[ivanvovk]

@aniketp02 Hey! Which HiFi-GAN version do you use? Checkpoint we provide in this repo is trained on LJSpeech only.

[aniketp02]

@ivanvovk Thanks for pointing that out; I was indeed using the checkpoint provided in this repo. Using the Universal HiFi-GAN checkpoint certainly improves the results!!

sagar_gen.mov

[ivanvovk]

@aniketp02 glad to hear it helped! For even better quality you can finetune HiFi-GAN on outputs of Grad-TTS.