{"adoption": {"forks": 471, "observed_at": "2026-08-28T04:06:33.353102+00:00", "stars": 2274}, "canonical_url": "https://ross.abutalabs.com/products/subword-nmt", "card": {"archived": false, "artifact_type": "library", "description": "Unsupervised Word Segmentation for Neural Machine Translation and Text Generation", "domain": ["machine-learning", "developer-tools"], "enriched": true, "function": ["nlp", "parser", "cli", "machine-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["rsennrich/subword-nmt"], "name": "rsennrich/subword-nmt", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2024-08-07T14:21:16+00:00", "repo": "rsennrich/subword-nmt", "stars": 2274, "tags": ["bpe", "subword-segmentation", "tokenization", "neural-machine-translation", "preprocessing", "natural-language-processing"], "topics": ["neural-machine-translation", "segmentation", "machine-translation", "nmt", "subword-units", "bpe"], "urls": [], "use_cases": ["learn bpe codes for machine translation preprocessing", "segment text into subword units for nmt", "tokenize text with byte pair encoding", "build joint bpe vocabulary for multiple languages", "segment rare words into character n-grams", "preprocess training data for neural text generation"], "what_it_is": "A Python library and CLI toolset for unsupervised word segmentation into subword units, best known for byte pair encoding (BPE) used in neural machine translation preprocessing. It provides commands to learn BPE codes, apply segmentation, and build vocabularies.", "when_to_avoid": ["you need modern tokenizers like SentencePiece or HuggingFace tokenizers with faster implementations", "you need trained subword models bundled with pretrained vocabularies", "you need runtime tokenization integrated into a model inference pipeline"], "when_to_choose": ["you need the classic BPE subword segmentation for NMT pipelines", "you want a simple pip-installable CLI for tokenization preprocessing", "you need reproducible segmentation for research experiments"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/subword-nmt", "repo": "rsennrich/subword-nmt", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:33.353102+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:41:32.719239+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e301db657a77ef5c83c668ab330bb7ad9b01ad8c07dc93cec1a81388ce8dfdfc", "fetched_at": "2026-08-28T04:06:33.353102+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rsennrich/subword-nmt"}, {"content_hash": "9bad1e31bb77d950d27aeb803c9d3c01e3c4360579aec5a77bde7ed3de964649", "fetched_at": "2026-08-29T10:22:01.063074+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/subword-nmt/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4019, "days_push": 756, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}