TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch.
Jeff HwangMoto HiraCaroline ChenXiaohui ZhangZhaoheng NiGuangzhi SunPingchuan MaRuizhe HuangVineel PratapYuekai ZhangAnurag KumarChin-Yun YuChuang ZhuChunxi LiuJacob KahnMirco RavanelliPeng SunShinji WatanabeYangyang ShiYumeng TaoRobin ScheiblerSamuele CornellSean KimStavros PetridisPublished in: CoRR (2023)