Lists (2)
Stars
Implementation of NAACL 2024 Outstanding Paper "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"
Musical mel transform for semi/quarter-tone features, written in ONNX-compatible PyTorch for audio AI neural networks
An implementation of local windowed attention for language modeling
An open agentic system built on smolagents, integrating multimodal state-of-the-art music AI models for understanding, generation, and interaction.
SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
Self-supervised key estimation model that matches performance with supervised state-of-the-art model.
An extremely fast Python package and project manager, written in Rust.
Modelling And Generating Harmonic Progressions With a Transformer And Voicing Encodings
Vector (and Scalar) Quantization, in Pytorch
A concise but complete full-attention transformer with a set of promising experimental features from various papers
A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.
[PyTorch] Minimal codebase for MusicGen models
Official implementation of "Equivariant Self-Supervision for Musical Tempo Estimation (ISMIR 2022)"
Code for the paper Cluster and Separate: A GNN Approach to Voice and Staff Prediction for Score Engraving
A PyTorch Library for Multi-Task Learning
The Jazz Trio Database is a dataset composed of about 45 hours of jazz performances annotated by an automated signal processing pipeline.
Encode and decode audio samples to/from compressed latent representations!
A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.
A collection of loss functions for medical image segmentation