A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)
This release includes LJSpeech pre-trained models:
hifi_lj.zip
: HiFi-GANps_normal_exp.zip
: PortaSpeech (normal version)ps_small_exp.zip
: PortaSpeech (small version)ds_exp.zip
: DiffSpeechaux_exp.zip
: a pre-trained FastSpeech2 checkpoint for training DiffSpeech