Make some noise and record your voice! Deep Learning models will analyze and build a drum kit, then start generating drum patterns infinitely with your sound.
Convolutional Neural Network is used to analyze and classify audio segments based on spectrograms (demo codepen) and Recurrent Neural Network(LSTM) for generating drum sequences. Shout-out to Tero Parviainen! Rhythm generation part of this codepen is based on his amazing Neural Drum Machine
Built with magenta.js, tensorflow.js and p5.js by @naotokui_en
This Pen is a fork, but the parent Pen has been deleted.