The official code repository for LeVo: High-Quality Song Generation with Multi-Preference Alignment

Video editing with Python

zero-shot voice conversion & singing voice conversion, with real-time support

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

High-speed downloader for multiple platforms

VC Without Retrain!

API for a Vocal Remover that uses Deep Neural Networks.

在浏览器中解锁加密的音乐文件。原仓库： 1. https://github.com/unlock-music/unlock-music ；2. https://git.unlock-music.dev/um/web

Port of OpenAI's Whisper model in C/C++

Robust Speech Recognition via Large-Scale Weak Supervision

Audio Coding Notebooks and Tutorials

C++ library for reading and writing of numpy's .npy files

Python DSP module

DDSP: Differentiable Digital Signal Processing

some attention implements

A Python example For Acoustic Howling Suppression

A cross-platform framework for developing spatial audio algorithms and software in C/C++

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

Muzic: Music Understanding and Generation with Artificial Intelligence

Lightweight C/C++ Extended Kalman Filter with Python for prototyping

autocorrelation-based O(NlogN) pitch detection

Opencpop: A High-Quality Open Source Chinese Popular Song Database for Singing Voice Synthesis

Traditional Speech Enhancement Methods

Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filte…

Acoular - Acoustic testing and source mapping software

Implementation related to the Deep Complex Networks

A 10000+ hours dataset for Chinese speech recognition

Oboe is a C++ library that makes it easy to build high-performance audio apps on Android.