# Lightweight NLP

This is a fine-tuned DistilBERT model for text keyword extraction, specifically designed to identify and extract keywords from English text.

One of the small BERT models released by Google Research, English-only, case-insensitive, trained with WordPiece masking.

A CPU-optimized small English language processing pipeline provided by spaCy, including core functionalities such as tokenization, part-of-speech tagging, dependency parsing, and named entity recognition

A distilled version of the RoBERTa model that retains the main performance of the original while reducing computational resource requirements.