Official repository of Evolutionary Optimization of Model Merging Recipes

PyTorch Implementation of DSB for Score Based Generative Modeling. Experiments managed using Hydra.

An Open-source Streaming High-fidelity Neural Audio Codec

Python parser and tools for MUSDB18 Music Separation Dataset

Spotify Scraper to extract all the information from spotify, download mp3 with cover of the song

music generation with masked transformers!

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

Simple text to phones converter for multiple languages

This is the official repository for M2UGen

Single channel speech source separation by diffusion process (ICASSP 2023)

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

AI based tool to convert vocals lyrics and pitch from music to autogenerate Ultrastar Deluxe, Midi and notes. It automatic tapping, adding text, pitch vocals and creates karaoke files.

Refactored version of https://github.com/ming024/FastSpeech2

The source code for the paper XiaoiceSing2 (interspeech2023)

text to speech using autoregressive transformer and VITS

Neural network-based singing voice synthesis library for research

vits2 backbone with bert

Billboard charts data

Official implementation of the paper "Unifying GANs and Score-Based Diffusion as Generative Particle Models", NeurIPS 2023

Code for Pre-training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction (https://arxiv.org/abs/2301.12068)

Music Pitch detection using Tensorflow SPICE model.

Official implementation of "Equivariant Self-Supervision for Musical Tempo Estimation (ISMIR 2022)"

Official PyTorch implementation of Contrastive Learning of Musical Representations

CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)

Self-supervised learning for real-time pitch estimation

a co-creative looper that uses generative modeling to **not** repeat itself.

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…

Singing Voice Synthesis based on VITS, different from VISinger