A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS
text-to-speech
deep-learning
unsupervised
pytorch
tts
speech-synthesis
transformer
supervised
multi-speaker
sota
comprehensive
single-speaker
neural-tts
non-autoregressive
fastspeech
fastspeech2
hifi-gan
non-ar
mel-gan
ultimate-tts
-
Updated
Sep 24, 2022 - Python