* Replaced PyTorch weight_norm With parametrizations.weight_norm * TorchAudio: Migrating The I/O Functions To Use The Dispatcher Mechanism * Corrected Code Style --------- Co-authored-by: Eren Gölge <erogol@hotmail.com>
* Return Dict from tts formatters * Make style
VITS model implementation built on Glow TTS and HiFiGAN layers.