Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English

Official repository of SepReformer for speech separation

Target Speaker Extraction Toolkit

Brand new TTS solution

🔥LeetCode solutions in any programming language | 多种编程语言实现 LeetCode、《剑指 Offer（第 2 版）》、《程序员面试金典（第 6 版）》题解

speaker conditioned voice activity detection

In defence of metric learning for speaker recognition

端到端语音唤醒工具箱，从模型训练到模型推理。

Production First and Production Ready End-to-End Keyword Spotting Toolkit

Simple implementation of mean shift clustering in python

🔈 Deep Learning & 3D Convolutional Neural Networks for Speaker Verification

聚类算法。实现Kmeans，DBSCAN以及谱聚类

Graph Convolutional Networks in PyTorch

《Pytorch模型训练实用教程》中配套代码

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 repo summarizes the tutorials, datasets, papers, codes and tools for speech separation and speaker extraction task. You are kindly invited to pull requests.

Room Impulse Response Generator

my open source audio edit software

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face D…

Trained models for the face_recognition python library

The world's simplest facial recognition api for Python and the command line

Deep learning face detection and recognition, implemented by pytorch. (pytorch实现的人脸检测和人脸识别)

一款入门级的人脸、视频、文字检测以及识别的项目.

Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities