natasha/navec

Compact high quality word embeddings for Russian language

51
/ 100
Established

Navec provides compact, high-quality word embeddings for the Russian language. It helps developers working with Russian text data by converting words into numerical representations, which can then be used in various natural language processing tasks. This allows for faster loading and less memory usage compared to other models, benefiting those building applications that process or analyze Russian text.

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

Use this if you are developing applications that need to process or understand Russian text efficiently and require accurate word representations while minimizing model size and load times.

Not ideal if your application requires extremely fast individual word lookups, as Navec involves a small amount of extra computation compared to simpler word2vec models.

Russian-NLP text-analysis machine-translation information-retrieval sentiment-analysis
Stale 6m
Maintenance 0 / 25
Adoption 12 / 25
Maturity 25 / 25
Community 14 / 25

How are scores calculated?

Stars

216

Forks

20

Language

Python

License

MIT

Last pushed

Jul 24, 2023

Commits (30d)

0

Dependencies

1

Reverse dependents

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/natasha/navec"

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