Paper, Code and Implementations

Few-shot word acquisition on SpokenCOCO

Before getting started, download the QbERT code for pair mining and extract within the model project  folder. For example, after cloning the QbERT repo, your directory structure should look like this: 

 
few-shot_word_acquisition

↳ 5-shot_5-way

↳ 5-shot_40-way

10-shot_5-way

↳ 50-shot_5-way

100-shot_5-way

QbERT

To get the exact support sets we use,  download them here and extract in the specific model folder. For example:
100-shot_5-way/support_sets

Now download the specific models here:

Few-shot word acquisition for low-resource languages