Showing 1-4 of 4 projects
Matcha-TTS is a fast and efficient text-to-speech (TTS) architecture using a conditional flow matching approach.
An all-in-one model for offline and simultaneous speech recognition, translation, and synthesis.
An open-source text-to-speech library built using Transformer-based neural networks for high-quality speech synthesis.
A PyTorch-based framework for non-autoregressive text-to-speech synthesis, including PortaSpeech and DiffSpeech models.
Get weekly updates on trending AI coding tools and projects.