avidale/compress-fasttext

Tools for shrinking fastText models (in gensim format)

46
/ 100
Emerging

This project helps Natural Language Processing (NLP) practitioners and researchers make their word embedding models much smaller without losing significant accuracy. It takes large fastText word embedding models and outputs compressed versions that are easier to store, share, and use in resource-constrained environments. Data scientists and machine learning engineers working with text data will find this useful.

183 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to reduce the file size of your fastText word embedding models for easier deployment or faster loading, especially when working with many languages or large datasets.

Not ideal if you are working with older versions of gensim without updating, or if you require absolute, uncompromised model accuracy where even minor reductions are unacceptable.

natural-language-processing text-analytics machine-learning-deployment data-compression language-models
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 11 / 25

How are scores calculated?

Stars

183

Forks

12

Language

Jupyter Notebook

License

MIT

Last pushed

May 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/avidale/compress-fasttext"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.