PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.
text-to-speech
duration
pytorch
tts
speech-synthesis
vae
unsupervised-learning
glow
self-attention
neural-tts
non-autoregressive
transforer
non-ar
unsupervised-duration
-
Updated
Aug 3, 2021 - Python