2. Factorized TdnnPyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi
3. dropclass speakerDropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020
4. simple diarizerSimplified diarization pipeline using some pretrained models - audio file to diarized segments in a few lines of code
5. GE2E-LossPytorch implementation of Generalized End-to-End Loss for speaker verification