Search Results - RepositoryStats

2 results found Sort:

109

554

mit

Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)

voxceleb1 voxceleb2 ecapa-tdnn speaker-recognition speaker-verification

Created 2021-10-25

27 commits to main branch, last one about a year ago

other

A library built for easier audio self-supervised training, downstream tasks evaluation

nsynth pytorch audioset voxceleb1 urbansound8k audio-datasets speech-commands audio-pretraining pytorch-lightning audio-classification audio-representation self-supervised-learning audio-self-supervised-learning

Created 2022-03-31

177 commits to main branch, last one 2 months ago