Prepare yourselves – this weekend is when 87 million phones will vibrate, play a loud noise and generally be a massive ...

We implement the following features in this framework: Data processing for non-autoregressive Text-to-Speech using Montreal Forced Aligner. Convenient and scalable framework for training and inference ...

About A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.