matangover

Retrieval-based-Voice-Conversion-WebUI

Easily train a good VC model with voice data <= 10 mins!

ultimatevocalremovergui

GUI for a Vocal Remover that uses Deep Neural Networks.

Amphion

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 audio, music, and speech generation research and development.

beartype

Unbearably fast near-real-time hybrid runtime-static type-checking in pure Python.

so-vits-svc-5.0

Core Engine of Singing Voice Conversion & Singing Voice Clone

stable-audio-tools

Generative models for conditional audio generation

DDSP-SVC

Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

SALMONN

SALMONN: Speech Audio Language Music Open Neural Network

cam2ip

Turn any webcam into an IP camera

CLAP

Learning audio concepts from natural language supervision

Play

Free and open source singing game with song editor for desktop, mobile, and smart TV

ltu

Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

dasp-pytorch

Differentiable audio signal processors in PyTorch

nendo

The Nendo AI Audio Tool Suite

RMVPE

Multilingual-PR

Phoneme Recognition using pre-trained models Wav2vec2, HuBERT and WavLM. Throughout this project, we compared specifically three different self-supervised models, Wav2vec (2019, 2020), HuBERT (2021) and WavLM (2022) pretrained on a corpus of English speech that we will use in various ways to perform phoneme recognition for different languages with a network trained with Connectionist Temporal Classification (CTC) algorithm.

spleeterpp

A C++ Inference library for the Spleeter project

SpleeterRT

Real time monaural source separation base on fully convolutional neural network operates on Time-frequency domain.

musicfm

vocalsound

Dataset and baseline code for the VocalSound dataset (ICASSP2022).

FCPE

MossFormer

This repo provides the processed samples of the manuscript "MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-head Transformer with Convolution-augmented Joint Self-Attentions", which was submitted to ICASSP 2023.

MedleyVox

singing_transcription_ICASSP2021

The source code and pre-trained model of the paper "On the Preparation and Validation of a Large-scale Dataset"

BPE-Symbolic-Music

Code of the paper "Byte Pair Encoding for Symbolic Music" (EMNLP 2023). Better and faster music generation

MAEST

Pre-training, fine-tuning, and inference code with the MAEST models for music analysis applications.

wav-aec

Applying webrtc's acoustic echo cancellation (AEC) to audio files

duet-svs-diffusion

demuxr

rt-vamp-plugin-sdk

Real-time Vamp plugin SDK for C++20