neuml/staticvectors

🔢 Work with static vector models

36
/ 100
Emerging

This tool helps data scientists and NLP practitioners efficiently work with older, 'static' word vector models like Word2Vec or FastText. It takes existing models or raw text for training and allows you to use them for tasks like language identification or getting word embeddings. This is ideal for those who need fast, lightweight text processing, especially with less common languages or when modern, larger models are overkill.

Used by 2 other packages. No commits in the last 6 months. Available on PyPI.

Use this if you need to work with established word vector models quickly and easily, especially for tasks like language identification or when resource constraints or specific language support make newer models impractical.

Not ideal if your primary need is state-of-the-art performance with common languages using the latest Transformer-based language models.

natural-language-processing text-analysis language-identification word-embeddings low-resource-languages
Stale 6m
Maintenance 2 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 0 / 25

How are scores calculated?

Stars

37

Forks

Language

Python

License

Apache-2.0

Last pushed

Apr 21, 2025

Commits (30d)

0

Dependencies

4

Reverse dependents

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/neuml/staticvectors"

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