Deep Learning with PyTorch

Downloading the embeddings

The torchtext library abstracts away a lot of complexity involved in downloading the embeddings and mapping them to the right word. Torchtext provides three classes, namely GloVe, FastText, CharNGram, in the vocab module, that ease the process of downloading embeddings, and mapping them to our vocabulary. Each of these classes provides different embeddings trained on different datasets and using different techniques. Let's look at some of the different embeddings provided:

• charngram.100d
• fasttext.en.300d
• fasttext.simple.300d
• glove.42B.300d
• glove.840B.300d
• glove.twitter.27B.25d
• glove.twitter.27B.50d
• glove.twitter.27B.100d
• glove.twitter.27B.200d
• glove.6B.50d
• glove.6B.100d
• glove.6B.200d
• glove.6B.300d

The build_vocab ...