AI Music Generation - Model Explorer

Add model

R-VAE

Rhythm generator using Variational Autoencoder (VAE). Based on M4L.RhythmVAE by Nao Tokui, modded and extended to support simple and compound meter rhythms, with minimal amount of training data. Similarly to RhythmVAE, the goal of R-VAE is the exploration of latent spaces of musical rhythms. Unlike most previous work in rhythm modeling, R-VAE can be trained with small datasets, enabling rapid customization and exploration by individual users. R-VAE employs a data representation that encodes simple and compound meter rhythms. Models and latent space visualizations for R-VAE are available on the project's GitHub page: https://github.com/vigliensoni/R-VAE-models.

Year: 2022

Website: https://github.com/vigliensoni/R-VAE

Input types: MIDI

Output types: MIDI

Output length: 2 bars

AI Technique: VAE

Dataset: "The Future Sample Pack"

License type: GPLv3

Real time:

Free:

Open source:

Checkpoints:

Fine-tune:

Train from scratch:

#MIDI #small-dataset #open-source #low-resource #free #checkpoints

RAVE

RAVE is an audio processing/generativity based on deep learning. RAVE (Realtime Audio Variational autoEncoder) is a learning framework for generating a neural network model from audio data. RAVE allowing both fast and high-quality audio waveform synthesis (20x real-time at 48 kHz sampling rate on standard CPU). In Max and Pd, it is accompanied by its nn~ decoder, which enables these models to be used in real time for various applications, audio generativity/timbre transformation/transfer.

Year: 2022

Website: https://forum.ircam.fr/collections/detail/rave/

Input types: Audio

Output types: Audio

Output length: Variable / Audio buffer size

AI Technique: VAE

Dataset: N/A

License type: MIT

Real time:

Free:

Open source:

Checkpoints:

Fine-tune:

Train from scratch:

#small-dataset #open-source #free #checkpoints

SampleRNN

WIP

Year: 2016

Website: https://github.com/soroushmehr/sampleRNN_ICLR2017

Input types: Audio

Output types: Audio

Output length: Variable

AI Technique: Hierarchical Recurrent Neural Network (RNN)

Dataset: Not disclosed

License type: MIT

Real time:

Free:

Open source:

Checkpoints:

Fine-tune:

Train from scratch:

#small-dataset #open-source #free #checkpoints

Mustango

Mustango is an open-source Text-to-Music model with focus on fine controllability allowing to specify musical attributes such as key or chord sequences.

Year: 2023

Website: https://amaai-lab.github.io/mustango/

Input types: Text

Output types: Audio

Output length: 10 sec

AI Technique: Latent Diffusion

Dataset: MusicBench

License type: MIT/CC-BY-SA

Real time:

Free:

Open source:

Checkpoints:

Fine-tune:

Train from scratch:

#text-to-audio #text-prompt #small-dataset #open-source #free #checkpoints