- Stockholm, Sweden
-
02:05
(UTC +02:00) - carlthome.github.io/blog
- https://orcid.org/0000-0002-8225-5191
- @carlthome
- in/carlthome
- carl.thome
Starred repositories
ACE-Step: A Step Towards Music Generation Foundation Model
Audio registry with searchable list of packages containing Plugins, Presets and Projects.
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
Graph-oriented live coding language and music/audio DSP library written in Rust
Nix expressions for VSCode and OpenVSX extensions [maintainers: @deemp, @AmeerTaweel]
The GigaMIDI dataset, featuring 1.43M MIDI files and advanced annotations, tackles challenges in symbolic music generation with its extensive metadata and a new metric for assessing musical express…
Unified automatic quality assessment for speech, music, and sound.
Repository for the paper "Combining audio control and style transfer using latent diffusion", accepted at ISMIR 2024
Croissant is a high-level format for machine learning datasets that brings together four rich layers.
Pytorch implementation of automatic music transcription method that uses a two-level hierarchical frequency-time Transformer architecture (hFT-Transformer).
Static checker for GitHub Actions workflow files
A friendly programming language from the future
curtified / FluxMusicGUI
Forked from camenduru/FluxMusicText-to-Music Generation with Rectified Flow Transformer
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
InspireMusic: Music, Song, Audio Generation.
Cross-platform emulator collection distributed with Docker images.
A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.
Bundle Nix derivations to run anywhere! [maintainer=@matthewbauer, @Artturin]
This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.
Collection of image builders [maintainer=@Lassulus]
Flexible LoRA Implementation to use with stable-audio-tools
BeatBrewer is an innovative drum beat generation tool powered by Denoising Diffusion Probabilistic Models (DDPM). This model crafts unique, dynamic, and high-quality drum beats for music producers,…
The Song Describer dataset is an evaluation dataset made of ~1.1k captions for 706 permissively licensed music recordings.
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Editor and Runtime modules that aim to add some Digital Audio Workstation capabilities to Unreal Engine 5, requires Unreal Editor 5.4
This is a hands-on lab/seminar, which complements the technologies and methodologies covered by the core courses of the SMC Master's program.