{"data":{"slug":"bheinzerling-bpemb","name":"bpemb","tagline":"Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)","github_url":"https://github.com/bheinzerling/bpemb","owner":"bheinzerling","repo":"bpemb","owner_avatar_url":"https://avatars.githubusercontent.com/u/4348795?v=4","primary_language":"Python","stars":1221,"forks":100,"topics":["embeddings","multilingual","natural-language-processing","nlp","subword-embeddings"],"archived":false,"github_pushed_at":"2024-10-01T02:49:47+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/bheinzerling-bpemb","markdown_url":"https://www.graphcanon.com/tools/bheinzerling-bpemb.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bheinzerling-bpemb","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bheinzerling-bpemb","description":"Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)","homepage_url":"https://nlp.h-its.org/bpemb","license":"MIT","open_issues":6,"watchers":23,"ai_summary":null,"readme_excerpt":null,"github_created_at":"2017-10-04T13:03:23+00:00","created_at":"2026-07-11T11:31:12.974046+00:00","updated_at":"2026-07-12T03:08:45.497544+00:00","categories":[{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"embeddings","name":"embeddings"},{"slug":"nlp","name":"nlp"},{"slug":"python","name":"python"},{"slug":"multilingual","name":"multilingual"},{"slug":"subword-embeddings","name":"subword-embeddings"},{"slug":"natural-language-processing","name":"natural-language-processing"}],"trust":{"provenance":{"is_fork":false,"github_id":105769029,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T11:31:13.679Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":null,"days_since_push":648,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:31:14.326Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T11:31:14.032Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-11T11:31:14.032Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T11:31:14.032Z"}}}}