🧠+🎧 Build your music algorithms and AI models with the next-gen DAW 🔥

Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.

OpenMusic: SOTA Text-to-music (TTM) Generation

List of academic resources on Multimodal ML for Music

Tegridy MIDI Dataset for precise and effective Music AI models creation.

Local windowed attention multi-instrumental music transformer for supervised music generation

The sampler that dreams. AI-powered VST3 for real-time music generation. Generate tempo-synced loops, trigger via MIDI, sculpt the unexpected. 8-track sampler meets infinite sound engine. No pre-made tracks—just raw material you control. Play with AI. Stay human.

Official implementation of "Contrastive Audio-Language Learning for Music" (ISMIR 2022)

SOTA Google's Perceiver-AR Music Transformer Implementation and Model

[SOTA] [92% acc] 786M-8k-44L-32H multi-instrumental music transformer with true full MIDI instruments range, efficient encoding, octo-velocity and outro tokens

SOTA kilo-scale MIDI dataset for MIR and Music AI purposes

Full-attention multi-instrumental music transformer featuring asymmetrical encoding with octo-velocity, and chords counters tokens, optimized for speed and performance

GPT3-based Multi-Instrumental MIDI Music AI Implementation

A Bach music generator with Artificial Intelligence. This model is made by a VQ-VAE + Transformer (decoder-only). Sequences of midi 1 quarter length are compressed into 16 codebooks via VQ-VAE and a transformer learns how to generate the codebooks sequence to obtain a midi score.

[DEPRECIATED] [PyTorch 2.0] [638M] [85.33% acc] Full-attention multi-instrumental music transformer for supervised music generation, optimized for speed, efficiency, and performance

SOTA Piano Transformer model trained on 4.2GB of Solo Piano MIDI music

Official implementation of "Equivariant Self-Supervision for Musical Tempo Estimation (ISMIR 2022)"

Do Music Generation Models Encode Music Theory? (ISMIR 2024)

Music AI implementation and model to split mixed Piano compositions into separate parts for each hand

[DEPRECIATED] Symbolic MIDI Music AI implementation

Front-end for symbolic music AI models

Local windowed attention multi-instrumental music transformer tailored for music orchestration/instrumentation and stable music generation

[DEPRECEATED] Multi-Instrumental Music Transformer trained on 12GB/400k MIDIs

[DEPRECEATED] Morpheus Music AI implementation spin-off :)

[DEPRECEATED] A miniature replica of OpenAI's MuseNet

[DEPRECIATED] Very fast, large music transformer with 8k sequence length, efficient heptabit MIDI notes encoding, true full MIDI instruments range, chords counters and outro tokens

Melody-Lyric-Generator is a tool for generating cohesive musical compositions by integrating melody generation and lyric creation. It leverages machine learning models, including fine-tuned GPT-2, and datasets like MAESTRO to produce high-quality melodies and Spanish-language lyrics.

Deploy Audiocraft Musicgen on Amazon SageMaker using SageMaker Endpoints for Async Inference.

[DEPRECEATED] Piano Transformer model trained on 2.6GB of MIDI piano music

Algorithmic and AI MIDI Drums Generator Implementation