dima806's picture
Update README.md
7374242 verified
metadata
metrics:
  - accuracy
  - roc_auc
base_model:
  - facebook/wav2vec2-base-960h

Currently, the model returns the confidence score that the input audio is created by one of the following classical composers found in MusicNet Dataset - a curated collection of 330 freely-licensed labeled classical music recordings - used for the training of this model:

More details in my Kaggle notebook and my Medium post.