Tweeted By @facebookai

Text-to-speech systems across the industry typically rely on GPUs or specialized hardware to generate state-of-the-art speech in real-time production. We solved core efficiency challenges to process 1 second of audio in 500 milliseconds — using only CPUs. https://t.co/qBMXIjOT0y

— Facebook AI (@facebookai) May 15, 2020