amanteur

whisper-medusa

Whisper with Medusa heads

RustPython

A Python Interpreter written in Rust

mira

MiRA (Music Replication Assessment) tool is a model-independent open evaluation method based on four diverse audio music similarity metrics to assess exact data replication of the training set.

stemgen

Examples for ICASSP2024 paper "StemGen: A music generation model that listens"

SepReformer

Official repository of SepReformer for speech separation

LibriSpace

awesome-music

Awesome Music Projects

mamba.py

A simple and efficient Mamba implementation in pure PyTorch and MLX.

project-NN-Pytorch-scripts

see README

Dasheng

Source for the Interspeech 2024 Paper "Scaling up masked audio encoder learning for general audio classification"

CoMoSVC

CoMoSVC: One-Step Consistency Model Based Singing Voice Conversion & Singing Voice Clone

DJCM

polars

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

bandit-v2

Reimplementation of Bandit for "Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support"

CoverHunter

Official PyTorch implementation of CoverHunter

whisper-finetune

Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.

query-bandit

Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems

hearinganythinganywhere

Hearing Anything Anywhere Code Release

encodecmae

Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'

SemantiCodec-inference

Ultra-low bitrate neural audio codec (0.31~1.40 kbps) with a better semantic in the latent space.

streamlit-audio-recorder

Record Audio from the User's Microphone in Apps that are Deployed to the Web. (via Browser Media-API, REACT-based, Streamlit Custom Component)

ssamba

The official implementation of SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model

Audio-Mamba-AuM

Official Implementation of the work "Audio Mamba: Bidirectional State Space Model for Audio Representation Learning"

soundata

Python library for downloading, loading & working with sound datasets

speechbrain

A PyTorch-based Speech Toolkit

instruct-MusicGen

The official implementation of our paper "Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning".

awesome-diarization

A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.

MusicGPT

Generate music based on natural language prompts using LLMs running locally

images-that-sound

Official repo for Images that sound: a special spectrogram that can be seen as images and played as sound generated by diffusions

ThunderKittens

Tile primitives for speedy kernels