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

A PyTorch-based Speech Toolkit

End-to-End Speech Processing Toolkit

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

A python package to build AI-powered real-time audio applications

This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit

turnkey self-hosted offline transcription and diarization service with llm summary

Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.

Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.

speaker diarization by uis-rnn and speaker embedding by vgg-speaker-recognition

This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.

Open source inference code for Rev's model

End-to-End Neural Diarization

Aims to create a comprehensive voice toolkit for training, testing, and deploying speaker verification systems.

Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196

speechlib is a library that can do speaker diarization, transcription and speaker recognition on an audio file to create transcripts with actual speaker names.

Time delay neural network (TDNN) implementation in Pytorch using unfold method