Latest / Kana & Mari's SoundRepos (English)

ivanvovk/durian-pytorch
DurIAN is a PyTorch implementation of a Duration Informed Attention Network for text-to-speech synthesis. It provides a duration-aware encoder-decoder model and a baseline variant, training with phoneme-level duration alignments, mel-spectrogram reconstruction losses, TensorBoard logging, checkpointing, validation, and Griffin-Lim-based inference.
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.