Xmins

CDGCN

CDGCN is a optimized graph-based clustering method. The basic concept of the CDGCN is to estimate the topological connection of speech segments and use a community detection algorithm to find the optimal partitions.

MISP-2023-Challenge-Baseline

Conv-TasNet

VBx

Variational Bayes HMM over x-vectors diarization

jsalt2019-diadet

Repository of recipes for the JSALT2019 workshop on "Speaker Detection in Adverse Scenarios with a Single Microphone"

self_supervised_AHC

Contains code for Deep Self Supervised Heirarchical Clustering for Speaker Diarization

OSDC

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

kaldi

kaldi-asr/kaldi is the official location of the Kaldi project.

conformer

[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

EEND

End-to-End Neural Diarization

EEND_PyTorch

A PyTorch implementation of End-to-End Neural Diarization