TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A SoundFont MIDI synthesizer for .NET

PyTorch Implementation of TCSinger(EMNLP 2024): Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control

Composer's Assistant for REAPER

Python bindings for TinySoundFont, a SoundFont MIDI synthesizer.

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Open singing synthesis platform / Open source UTAU successor

PyTorch Implementation of TCSinger 2(ACL 2025): Customizable Multilingual Zero-shot Singing Voice Synthesis

STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation

A SoundFont MIDI synthesizer written in pure Python

An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

Zong! Music Notation

Implementation of RIFT-SVC, a singing voice conversion model based on Rectified Flow Transformer.

Code and demo for paper: Zhao et al., AccoMontage-3: Full-Band Accompaniment Arrangement via Sequential Style Transfer and Multi-Track Function Prior.

CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model

Source code to pbrt, the ray tracer described in the forthcoming 4th edition of the "Physically Based Rendering: From Theory to Implementation" book.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Muzic: Music Understanding and Generation with Artificial Intelligence

Source code for pbrt, the renderer described in the third edition of "Physically Based Rendering: From Theory To Implementation", by Matt Pharr, Wenzel Jakob, and Greg Humphreys.

Simple Scalable Discrete Diffusion for text in PyTorch

Annotated Flow Matching paper

The Autograd Engine

[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

Educational implementation of the Discrete Flow Matching paper