SAVRN
Search Contact SAVRN

Organization

Music Technology Group (Universitat Pompeu Fabra)

mtg-upf

Sound synthesis | Audio source separation | Audio feature analysis | Corpora and datasets | Software engineering | Computational analysis of sound events | Music classification | Music retrieval | Multimodal music processing | Musical interface design | Computational music creativity | Computational musicology | Music performance analysis | Music technologies for health and well-being

Models in Library1
Datasets in Library0
Models on Hugging Face39
Followers34

Models

MAEST is a family of Transformer models based on PASST and focused on music analysis applications. The MAEST models are also available for inference in the Essentia library and for inference and training in the official repository. You can try the MAEST interactive demo on replicate. MAEST is a music audio representation model pre-trained on the task of music style classification. According to the evaluation reported in the original paper, it reports good performance in several downstream music analysis tasks. The MAEST models can make predictions for a taxonomy of 400 music styles derived from the public metadata of Discogs. The MAEST models have reported good performance in downstream…

Open weights cc-by-nc-sa-4.0 86M parameters transformers