When will mixer_tts pretrained model added?

[yuananf]

I'd like to test it when it's possible. As said in the paper, it has a small number of parameters and enable much faster speech synthesis compared to the models with similar quality.

[XuesongYang]

mixer_tts pretrained model checkpoint has already been released. Please try,

from nemo.collections.tts.models import MixerTTSModel

print(MixerTTSModel.list_available_models())

you will find "tts_en_lj_mixertts" which is the one you are interested in. We have a tutorial on how to train mixer_tts as well: https://github.com/NVIDIA/NeMo/blob/main/tutorials/tts/FastPitch_MixerTTS_Training.ipynb