Keunwoo Choi

kapre. kapre: Keras Audio Preprocessors

music-auto_tagging-keras. Music auto-tagging models and trained weights in keras/theano

transfer_learning_music. Transfer learning for music classification and regression tasks

dl4mir. Deep learning for MIR

torchaudio-contrib. A test bed for updates and new features | pytorch/audio

lstm_real_book. LSTM source code to generate jazz chord progressions

DrummerNet. Supplementary material of "Deep Unsupervised Drum Transcription", ISMIR 2019

LSTMetallica. LSTM to generate drum tracks based on Metallica's midi drum tracks

ismir-2019-posters.

residual_block_keras. Residual network block in Keras

magnatagatune-list. List of automatic music tagging research articles that are evaluated against MagnaTagATune Dataset

keras_STFT_layer. Do STFT in Keras

keras_callbacks_example. Keras callback example

MSD_split_for_tagging. Python

Auralisation. Auralisation of learned features in CNN (for audio)

awesome-audio-study-materials-for-korean.

music4all_contrib. Jupyter Notebook

data-science-handbook. 데이터 과학 핸드북

perceptual_weighting. Loudness compensation for time-frequency representation

ismir2016-ldb-audio-captioning-model-keras. Audio captioning RNN model in Keras

tokenizer-vs-tokenizer.

icassp_2017.

how-to-organize-ismir.

keras_cropping_layer. Keras cropping layer implementation

UrbanSound8K-preprocessing. Jupyter Notebook

frequency-aware-conv2d-layer-pytorch. Python

awesome-conscious-AIs.

pytorch-dataset-combinators. Python

audioset-downloader. Python downloader for Google AudioSet with `youtube_dl`

librosa. Python library for audio and music analysis

machine_learning_eng2kor. Machine learning eng2kor word dictionary

demucs. Code for the paper Hybrid Spectrogram and Waveform Source Separation

FMA_convnet_features. FMA convnet features

open-unmix-pytorch. Open-Unmix - Music Source Separation for PyTorch

magnatagatune. yeah

fma. FMA: A Dataset For Music Analysis

openmic-2018-tfrecord. Python

torch-audiomentations. Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

audioset_tagging_cnn. Python

AudioDataset. Dataset of Music21 & AudioSet & VGGSound

vggsound_download. download the vggsound dataset

sequence-layers-pytorch. Python

relative-position-pytorch. a pytorch implementation of self-attention with relative position representations

torchdata. A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

dataloaders. Pytorch and TensorFlow data loaders for several audio datasets

frechet-audio-distance. A lightweight library of Frechet Audio Distance calculation.

torchvggish. Pytorch port of Google Research's VGGish model used for extracting audio features.

sf_segmenter. Music segmentation algorithm, based on SF (structural feature)

ddsp. DDSP: Differentiable Digital Signal Processing

audioset_augmentor. Sound augmentation using Large-scale audio dataset (Audioset)

audioset-dl. Download AudioSet for Vision-Audio-Text Pre-training

audiocaps. 🔊 Repository for our NAACL-HLT 2019 paper: AudioCaps

the-pile. Python

Open-Llama. The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.

AudioLDM-training-finetuning. AudioLDM training, finetuning, evaluation and inference.