pier-maker92/bachsformer
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.
This project helps musicians, composers, or musicologists generate new musical pieces in the style of J.S. Bach. It takes Bach's MIDI compositions as input and creates entirely new MIDI scores that capture his distinct musical vocabulary. The primary users would be those interested in algorithmic composition, musical research, or exploring creative variations on existing classical works.
No commits in the last 6 months.
Use this if you want to automatically generate new, Bach-like musical compositions in MIDI format without needing deep musical theory knowledge or traditional composition skills.
Not ideal if you need to generate music in a genre other than Bach's style, require precise control over every note, or are looking for a tool to help with human-assisted composition.
Stars
44
Forks
6
Language
Python
License
MIT
Category
Last pushed
Sep 21, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/pier-maker92/bachsformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
multimodal-art-projection/YuE
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
hugofloresgarcia/vampnet
music generation with masked transformers!
asigalov61/SuperPiano
Absolutely amazing SOTA Google Colab (Jupyter) Notebooks for creating/training SOTA Music AI...
sedthh/BeatLearning
Open Source Generative AI Models for Automatic Rhythm Game Beatmap Generation (for acoustic people)
AlekseyKorshuk/huggingartists
Lyrics generation with GPT2-based Transformer