skinny.

Latest / Kana & Mari's SoundRepos (English)

rishikksh20/AdaSpeech | adaptive custom voice text to speech | GitHub

An unofficial PyTorch implementation of AdaSpeech focused on single-speaker adaptive text-to-speech and improved FastSpeech 2 acoustic generalization. It provides preprocessing, training, evaluation, inference, acoustic feature prediction, TorchScript export, and waveform synthesis through MelGAN, WaveGlow, or Griffin-Lim. Related: rishikksh20/AdaSpeech / adaptive custom voice text to speech / GitHub

The skinny

The skinny isn't ready yet — notes appear once the transcript is processed.