This is an implementation of the Google's Vision Transformer large patch 32 that is used for music classification into different genres. The dataset used is the gtzan dataset which has melspectrograms of many songs.

faba7b5 verified about 2 years ago

preview code

raw

history blame contribute delete

167 Bytes

metadata

license: apache-2.0
datasets:
  - ghermoso/egtzan_plus
metrics:
  - accuracy
library_name: transformers
pipeline_tag: image-classification
tags:
  - ViT
  - music
  - CV