VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Ongoing research training transformer models at scale

The official Vim repository

DeepGEMM: clean and efficient BLAS kernel library on GPU

Fast and memory-efficient exact attention

State-of-the-art 2D and 3D Face Analysis Project

An unofficial PyTorch implementation of the audio LM VALL-E

A 10000+ hours dataset for Chinese speech recognition

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

Simple conversion and localization between simplified and traditional Chinese using tables from MediaWiki.

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

Code for the paper Hybrid Spectrogram and Waveform Source Separation

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

A fully working pytorch implementation of NaturalSpeech (Tan et al., 2022)

Ongoing research training transformer language models at scale, including: BERT & GPT-2

A lightweight tar library written in ANSI C

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.