music-classification / tutorial
2021 ISMIR tutorial - music classification
☆141Updated 2 years ago
Related projects: ⓘ
- ☆92Updated 2 years ago
- Perform transfer learning for MIR using Jukebox!☆171Updated 11 months ago
- Emotional conditioned music generation using transformer-based model.☆138Updated last year
- Tools and tutorials for the OpenMIC-2018 dataset.☆89Updated 2 years ago
- Multi-Track Music Generation with the Transfomer and the Johann Sebastian Bach Chorales dataset☆120Updated 6 months ago
- Official implementation of "Contrastive Audio-Language Learning for Music" (ISMIR 2022)☆103Updated last year
- Results and Models for Learning Audio Representations of Music Content☆87Updated 3 months ago
- ☆120Updated 4 years ago
- Accompanying code for our ISMIR 2020 paper on mood estimation.☆32Updated 2 years ago
- Simple collection of MIR datasets with metadata and links☆232Updated 4 months ago
- This is the official repository for the paper, MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding.☆176Updated 5 months ago
- A collection of useful audio datasets and transforms for PyTorch.☆130Updated last year
- ☆68Updated 2 years ago
- A simple library for Fréchet Audio Distance (FAD) calculation☆137Updated last week
- ☆158Updated 7 months ago
- Python scripts for modelling timbral attributes☆75Updated 3 months ago
- Jamendo music dataset with time-aligned lyrics for lyrics alignment evaluation☆72Updated 10 months ago
- ☆121Updated 3 years ago
- Official PyTorch implementation of Contrastive Learning of Musical Representations☆306Updated last month
- Source code for "MusCaps: Generating Captions for Music Audio" (IJCNN 2021)☆76Updated 2 years ago
- Audio transformations library for PyTorch☆220Updated 2 years ago
- A didactic toolkit to rapidly prototype audio classifiers with pre-trained Tensorflow models and Scikit-learn☆142Updated last year
- PyTorch wrappers for using your model in audacity!☆172Updated last year
- ☆71Updated last year
- Implementation of DDSP (PyTorch), Differentiable Digital Signal Processing (ICLR 2020)☆149Updated 3 years ago
- audioLIME: Listenable Explanations Using Source Separation☆33Updated 3 years ago
- ☆57Updated 3 years ago
- A project to synthesize massive amounts of multitrack audio data from MIDI.☆55Updated 4 years ago
- Metadata, scripts and baselines for the MTG-Jamendo dataset☆262Updated 2 months ago
- A dataset of 222 digital musical scores aligned with 1068 performances (more than 92 hours) of Western classical piano music.☆170Updated 2 months ago