Questions wav2vec - ufal/NPFL095 GitHub Wiki
- Why is the quantization module used in the paper? What is the purpose of codebooks?
- What is the difference between softmax and Gumbel softmax? Why is the Gumbel softmax used here?
- What kind of output qualities are observed by Contrastive loss? And what is the functionality of the Diversity loss?
- Find at least three examples of a set of classes into which the output of pre-trained models can be divided during fine-tuning.
- What is the difference between LARGE and BASE models described in the paper? Which one is a better choice to use and why?