YearnyeenHo

unsupervised_compositional_representations

ISMIR 24 Supplementary Material

music2latent

Encode and decode audio samples to/from compressed latent representations!

thegluenote

TheGlueNote is representation model for note-wise music alignment.

latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

muchomusic

MuChoMusic is a benchmark for evaluating music understanding in multimodal audio-language models.

beat_this

Accurate and general beat tracker

ChordSync

Code for ChordSync, a conformer-based audio-to-chord synchroniser

mar

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

jamendolyrics

Jamendo music dataset with time-aligned lyrics for lyrics alignment evaluation

LyricWhiz

[ISMIR 2023] LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT

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.

contriever

Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning

rectified-flow-pytorch

Implementation of rectified flow and some of its followup research / improvements in Pytorch

ttt-lm-pytorch

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

AudioTime

GAMA

Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

ears_dataset

Expressive Anechoic Recordings of Speech (EARS)

notebooks

Notebooks using the Hugging Face libraries 🤗

1d-tokenizer

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

PianoMotion10M

Code release for PianoMotion10M

LLM101n

LLM101n: Let's build a Storyteller

CompA

Code for ICLR 2024 Paper: CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models

FreeV

[InterSpeech 24] FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter

LLM-Codec

The open source code for LLM-Codec

soundctm

Pytorch implementation of SoundCTM

m2d

Masked Modeling Duo: Towards a Universal Audio Pre-training Framework

SparsePrimingRepresentations

Public repo to document some SPR stuff

big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

CV-VAE

CV-VAE: A Compatible Video VAE for Latent Generative Video Models

Synchformer

Efficient synchronization from sparse cues