# dav/word2vec

This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently used in many natural language processing applications and for further research.

Repository: https://github.com/dav/word2vec
Canonical: https://ross.abutalabs.com/products/dav-word2vec
Language: C
License: Apache-2.0
License Family: permissive
Last push: 2021-05-10T21:53:01+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": 4764, "days_push": 1941, "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 1741, forks 626 (observed 2026-08-28T04:05:30.258235+00:00)

## What it is
The original Google word2vec tool, hosted on GitHub with community patches for Mac OS X compilation and memory fixes. It efficiently trains word vector representations using CBOW and skip-gram architectures from a text corpus.

## Use cases
- train word embeddings from a text corpus
- compute vector representations of words with skip-gram
- compute word vectors with continuous bag-of-words
- explore word similarity interactively
- research natural language processing applications

## When to choose
- you need the classic, fast C implementation of word2vec
- you want to train word embeddings on your own corpus
- you need a lightweight command-line tool without Python dependencies

## When to avoid
- you need modern contextual embeddings like BERT or transformer models
- you want an actively maintained project with recent fixes
- you need deep integration with a Python ML pipeline

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, cli
- domain: machine-learning
- platform: cli
- tags: word-embeddings, word2vec, cbow, skip-gram, c, natural-language-processing, linux, macos

## Member repositories
- dav/word2vec (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:30.258235+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 2026-08-30T03:30:02.338347+00:00, confidence not recorded.
  - readme: https://github.com/dav/word2vec (fetched 2026-08-28T04:05:30.258235+00:00, sha d99978e6647f)
- Data as of 2026-08-30T08:39:29.467469+00:00.