AndongLi's starred repositories
flash-attention
Fast and memory-efficient exact attention
text-to-text-transfer-transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.
RectifiedFlow
Official Implementation of Rectified Flow (ICLR2023 Spotlight)
Meta-voicebox
Implementation of Meta-Voicebox : The first generative AI model for speech to generalize across tasks with state-of-the-art performance.
Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
pytorch_ema
Tiny PyTorch library for maintaining a moving average of a collection of parameters.
Text-to-sound-Synthesis
The source code of our paper "Diffsound: discrete diffusion model for text-to-sound generation"
SoundStorm
The reproduced code for Google's SoundStorm
Robust-E2E-ASR
This repository contains the code for our upcoming paper An Investigation of End-to-End Models for Robust Speech Recognition at ICASSP 2021.
Neural-Gradient-Regularizer
This repository contains official implementation of Neural Gradient Regularizer (NGR).