gpt-tokenizer
A pure JavaScript implementation of a BPE tokenizer (Encoder/Decoder) for GPT-2 / GPT-3 / GPT-4 and other OpenAI models
stopword
A module for node.js and the browser that takes in text and returns text that is stripped of stopwords. Has pre-defined stopword lists for 62 languages and also takes lists with custom stopwords as input.
wink-nlp
Developer friendly Natural Language Processing ✨