Mddct

jaxloudnorm

Jax implementation of a flexible audio loudness meter in Python with implementation of ITU-R BS.1770-4 loudness algorithm

julius

Fast PyTorch based DSP for audio and 1D signals

dm_aux

audiotools

Object-oriented handling of audio data, with GPU-powered augmentations, and more.

DAC-JAX

A JAX Implementation of the Descript Audio Codec

jaxrl

JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

multihost_dataloading

Experimenting with how best to do multi-host dataloading

SOFA

SOFA: Singing-Oriented Forced Aligner

tokenizers

Go bindings for HuggingFace Tokenizer

QQMusicSpider

基于Scrapy的QQ音乐爬虫(QQ Music Spider)，爬取歌曲信息、歌词、精彩评论等，并且分享了QQ音乐中排名前6400名的内地和港台歌手的49万+的音乐语料

legado

阅读APP书源

SALMONN

SALMONN: Speech Audio Language Music Open Neural Network

SpeechGPT

SpeechGPT Series: Speech Large Language Models

Awesome-instruction-tuning

A curated list of awesome instruction tuning datasets, models, papers and repositories.

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

ebook

电子书

MAP-NEO

HA2G

[CVPR 2022] Code for "Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation"

highway

Performance-portable, length-agnostic SIMD with runtime dispatch

iqiyi-parser

解析下载爱奇艺、哔哩哔哩、腾讯视频

TorchKMeans

A torch-based implementation of K-Means and K-Means++

torch_kmeans

PyTorch implementations of KMeans, Soft-KMeans and Constrained-KMeans which can be run on GPU and work on (mini-)batches of data.

ChatTTS

ChatTTS is a generative speech model for daily dialogue.

DeepFilterNet

Noise supression using deep filtering

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

xcodec

X-Codec: Unified Audio Tokenizer for Audio Language Model

music-dl

Music Searcher and Downloader. - 音乐搜索下载器。

UMOE-Scaling-Unified-Multimodal-LLMs

The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"

NExT-GPT

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

audio-ai-timeline

A timeline of the latest AI models for audio generation, starting in 2023!