Starred repositories
Self-hostable web app for isolating the vocal, accompaniment, bass, and drums of any song. Supports Spleeter, D3Net, Demucs, Tasnet, X-UMX. Built with React and Django.
tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)
Music recommender using deep learning with Keras and TensorFlow
A collection of experiments for exploring how music works, all built with the Web Audio API.
Kaggle | 1st place solution for Freesound Audio Tagging 2019
Audio samples accompanying publications related to Tacotron, an end-to-end speech synthesis model.
Notes on the Deep Learning book from Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016)
刷算法全靠套路,认准 labuladong 就够了!English version supported! Crack LeetCode, not only how, but also why.
Improved Wave-U-Net implemented in Pytorch
TensorFlow implementation for audio neural style.
TensorFlow CNN for fast style transfer ⚡🖥🎨🖼
This project is the group work of HKU COMP7404 Group A, it aims to transfer an input no-jazz song to a jazz style with the NMT model.
Music Style Transfer based on CycleGan
Build spectrogram and mel-spectrogram data sets from Free Music Archive data
Source code for "Transferring the Style of Homophonic Music Using Recurrent Neural Networks and Autoregressive Model"
Symbolic Music Genre Transfer with CycleGAN - Refactorization
CycleGAN timbre transfer and VGG16 music genre classification
Timbre Enhanced Multi modal Music Style Transfer
museval - source separation evaluation tools for python
Convolutional Neural Network for auto-tagging of audio clips on MagnaTagATune dataset
A TensorFlow implementation of "Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms"
Pytorch implementation of "Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms"
A TensorFlow+Keras implementation of "Sample-level CNN Architectures for Music Auto-tagging Using Raw Waveforms"
Music auto-tagging models and trained weights in keras/theano
DNN based singing voice synthesis
Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data