# Kyubyong/wordvectors

Pre-trained word vectors of 30+ languages

Repository: https://github.com/Kyubyong/wordvectors
Canonical: https://ross.abutalabs.com/products/wordvectors
Language: Python
License: MIT
License Family: permissive
Topics: vector, word2vec, language, fasttext
Last push: 2018-10-11T20:54:06+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3543, "days_push": 2883, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2234, forks 386 (observed 2026-08-28T04:06:29.277658+00:00)

## What it is
A collection of pre-trained word vector (word embedding) models for 30+ languages, built from Wikipedia dumps using Word2Vec and fastText. It also includes scripts for building corpora and training your own vectors.

## Use cases
- find pre-trained word vectors for non-English languages
- download word2vec embeddings for multilingual NLP
- get fastText vectors for languages like Bengali or Catalan
- train custom word embeddings from Wikipedia dumps
- semantic similarity across multiple languages

## When to choose
- you need word embeddings for an under-resourced or non-English language
- you want both word2vec and fastText variants trained on the same corpus
- you want reproducible scripts to build vectors from Wikipedia dumps

## When to avoid
- you need contextual embeddings like BERT or transformer-based models
- you need up-to-date vectors reflecting recent language usage (last release 2018)
- you only need English word vectors

## Facets
- artifact type: dataset
- maturity: maintenance
- function: nlp, machine-learning
- domain: machine-learning
- platform: python, cross-platform
- tags: word2vec, fasttext, word-embeddings, multilingual, pre-trained-models, wikipedia, natural-language-processing

## Member repositories
- Kyubyong/wordvectors (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.277658+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:44:20.906596+00:00, confidence not recorded.
  - readme: https://github.com/Kyubyong/wordvectors (fetched 2026-08-28T04:06:29.277658+00:00, sha c4ebe52e6165)
- Data as of 2026-08-30T08:39:29.467469+00:00.