아마존 연구팀은 지금까지 제작된 것 중 가장 큰 텍스트 음성 변환(TTS) 모델을 개발

A team of Amazon researchers has announced the development of the largest text-to-speech (TTS) model ever created, opening up new possibilities for artificial intelligence technology. The model, called BASE TTS, was trained on 100,000 hours of public domain speech data and has 980 million parameters. It is believed to be the largest model in the text-to-speech domain to date. For comparison, the..

원문링크 : 아마존 연구팀은 지금까지 제작된 것 중 가장 큰 텍스트 음성 변환(TTS) 모델을 개발