minzwon / sota-music-tagging-models
☆409Updated last year
Alternatives and similar repositories for sota-music-tagging-models:
Users that are interested in sota-music-tagging-models are comparing it to the libraries listed below
- Official PyTorch implementation of Contrastive Learning of Musical Representations☆316Updated 6 months ago
- Perform transfer learning for MIR using Jukebox!☆177Updated last year
- Metadata, scripts and baselines for the MTG-Jamendo dataset☆293Updated 7 months ago
- "A Bi-Directional Transformer for Musical Chord Recognition" accepted on ISMIR2019☆151Updated 4 years ago
- Simple collection of MIR datasets with metadata and links☆239Updated 9 months ago
- This is the official repository for the paper, MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding.☆187Updated 10 months ago
- The Harmonix Set: Beats, Downbeats, and Structural Annotations for Pop Music☆182Updated 2 months ago
- ☆186Updated last year
- Official implementation of the paper "Acoustic Music Understanding Model with Large-Scale Self-supervised Training".☆350Updated 10 months ago
- Python library for working with Music Information Retrieval datasets☆373Updated 2 months ago
- Synthesis of MIDI with DDSP (https://midi-ddsp.github.io/)☆306Updated 2 years ago
- DALI: a large Dataset of synchronised Audio, LyrIcs and vocal notes.☆354Updated 4 years ago
- ☆93Updated 3 years ago
- 2021 ISMIR tutorial - music classification☆146Updated 3 years ago
- Collection of audio-focused loss functions in PyTorch☆764Updated 6 months ago
- This is the dataset repository for the paper: POP909: A Pop-song Dataset for Music Arrangement Generation☆311Updated 4 years ago
- Audio Dataset for training CLAP and other models☆666Updated last year
- Emotional conditioned music generation using transformer-based model.☆148Updated 2 years ago
- A lightweight library for Frechet Audio Distance calculation.☆254Updated 5 months ago
- Efficient Training of Audio Transformers with Patchout☆318Updated last year
- Results and Models for Learning Audio Representations of Music Content☆97Updated 2 months ago
- Pronounced as "musician", musicnn is a set of pre-trained deep convolutional neural networks for music audio tagging.☆616Updated last year
- ☆185Updated 8 months ago
- A library for soundscape synthesis and augmentation☆394Updated 2 years ago
- Official implementation of Neural Audio Fingerprint (ICASSP 2021)☆189Updated 6 months ago
- Audio transformations library for PyTorch☆230Updated 2 years ago
- Python library for downloading, loading & working with sound datasets☆332Updated 4 months ago
- The official implementation of Theme Transformer. A Theme-based music generation. IEEE TMM☆122Updated 2 years ago
- Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch☆459Updated last year
- Evaluation functions for music/audio information retrieval/signal processing algorithms.☆624Updated this week