End-to-End Speech Processing Toolkit
-
Updated
Jun 18, 2024 - Python
End-to-End Speech Processing Toolkit
A PyTorch-based Speech Toolkit
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
speaker diarization by uis-rnn and speaker embedding by vgg-speaker-recognition
Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.
A python package to build AI-powered real-time audio applications
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196
End-to-End Neural Diarization
Time delay neural network (TDNN) implementation in Pytorch using unfold method
This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.
PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi
turnkey self-hosted offline transcription and diarization service with llm summary
Simplified diarization pipeline using some pretrained models - audio file to diarized segments in a few lines of code
PyTorch implementation of Densely Connected Time Delay Neural Network
Aims to create a comprehensive voice toolkit for training, testing, and deploying speaker verification systems.
Add a description, image, and links to the speaker-diarization topic page so that developers can more easily learn about it.
To associate your repository with the speaker-diarization topic, visit your repo's landing page and select "manage topics."