This repository provides a multi-mode and multi-speaker expressive speech synthesis framework, including multi-attentive Tacotron, DurIAN, Non-attentive Tacotron, GST, VAE, GMVAE, and X-vectors for building prosody encoder.
durian
tacotron
gst-tacotron
vae-tacotron
gmvae-tacotron
forward-attention-tacotron
non-attentive-tacotron
gmm-tacotron
-
Updated
Sep 21, 2022 - Python