Audio classification dataset - number of classes

šŸ¤—Datasets
1

I want to train an Audio Classifier from scratch using one of the datasets provided by huggingface, for example using librispeech_asr Ā· Datasets at Hugging Face. How do i determine the number of speaker IDs (ā€˜speaker_idā€™ field) so i can set the size of my final dense layer in my classifier?

2

Hi! You can call .unique("speaker_id") on the dataset object to find unique speaker ids.

1 Like