{"adoption": {"forks": 386, "observed_at": "2026-08-28T04:06:29.277658+00:00", "stars": 2234}, "canonical_url": "https://ross.abutalabs.com/products/wordvectors", "card": {"archived": false, "artifact_type": "dataset", "description": "Pre-trained word vectors of 30+ languages", "domain": ["machine-learning"], "enriched": true, "function": ["nlp", "machine-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["Kyubyong/wordvectors"], "name": "Kyubyong/wordvectors", "platform": ["python", "cross-platform"], "pushed_at": "2018-10-11T20:54:06+00:00", "repo": "Kyubyong/wordvectors", "stars": 2234, "tags": ["word2vec", "fasttext", "word-embeddings", "multilingual", "pre-trained-models", "wikipedia", "natural-language-processing"], "topics": ["vector", "word2vec", "language", "fasttext"], "urls": [], "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"], "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.", "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"], "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"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/wordvectors", "repo": "Kyubyong/wordvectors", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:29.277658+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:44:20.906596+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c4ebe52e616566890f6d590f2f8253fd19095cec157d6d63435d38d0b66c78a9", "fetched_at": "2026-08-28T04:06:29.277658+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Kyubyong/wordvectors"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3543, "days_push": 2883, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}