{"adoption": {"forks": 100, "observed_at": "2026-08-28T04:04:02.774957+00:00", "stars": 1224}, "canonical_url": "https://ross.abutalabs.com/products/bpemb", "card": {"archived": false, "artifact_type": "library", "description": "Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)", "domain": ["machine-learning"], "enriched": true, "function": ["nlp", "machine-learning", "parser"], "health_score": 20, "homepage": "https://nlp.h-its.org/bpemb", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["bheinzerling/bpemb"], "name": "bheinzerling/bpemb", "platform": ["python"], "pushed_at": "2024-10-01T02:49:47+00:00", "repo": "bheinzerling/bpemb", "stars": 1224, "tags": ["word-embeddings", "byte-pair-encoding", "subword-segmentation", "sentencepiece", "gensim", "pretrained-models", "multilingual-nlp", "natural-language-processing", "multilingual"], "topics": ["embeddings", "subword-embeddings", "natural-language-processing", "nlp", "multilingual"], "urls": [], "use_cases": ["get pretrained subword embeddings for low-resource languages", "segment text into byte-pair encoded subwords without tokenization", "initialize an embedding layer in PyTorch or TensorFlow for an NLP model", "handle out-of-vocabulary words in a neural NLP pipeline", "build a compact multilingual embedding model smaller than FastText", "encode sentences into subword IDs for downstream models"], "what_it_is": "BPEmb is a collection of pre-trained subword embeddings in 275 languages based on Byte-Pair Encoding, trained on Wikipedia, distributed as a Python library wrapping gensim KeyedVectors and SentencePiece models. It provides subword segmentation and embedding vectors intended as input layers for neural NLP models.", "when_to_avoid": ["you need state-of-the-art contextual embeddings like BERT or transformer models", "you only work with English and can use larger alternatives like FastText", "you need embeddings trained on domain-specific corpora rather than Wikipedia"], "when_to_choose": ["you need embeddings for many languages, especially low-resource ones", "you want small pretrained embeddings without tokenization or morphological analysis", "you need subword segmentation to handle unknown words in neural models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/bpemb", "repo": "bheinzerling/bpemb", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.774957+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:15:26.267590+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff3b8c318f3bccaca613b4396b9c84351ce69ea3ca0a53ab43238250e7fd4347", "fetched_at": "2026-08-28T04:04:02.774957+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bheinzerling/bpemb"}, {"content_hash": "c5ff35da94dede0fe0141f6a3367ee5fbbc2b7d397a57b447a74c2ea462cd4ef", "fetched_at": "2026-08-29T12:23:45.997855+00:00", "kind": "homepage", "missing": false, "url": "https://nlp.h-its.org/bpemb"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3255, "days_push": 701, "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}}