{"id":35843742,"url":"https://github.com/Sovichea/khmer_segmenter","last_synced_at":"2026-01-14T12:00:38.457Z","repository":{"id":331424651,"uuid":"1126568120","full_name":"Sovichea/khmer_segmenter","owner":"Sovichea","description":"A zero-dependency, high-performance Khmer word segmenter using the Viterbi algorithm. Optimized for dictionary accuracy, ultra-low memory footprint, and edge deployment.","archived":false,"fork":false,"pushed_at":"2026-01-07T17:17:44.000Z","size":47858,"stargazers_count":23,"open_issues_count":0,"forks_count":2,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-08T03:28:33.049Z","etag":null,"topics":["c-language","dictionary-based","khmer","khmer-language","khmer-nlp","lightweight","nlp","portable","python","tokenization","viterbi-algorithm","word-segmentation","zero-dependency","zig-build-system"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Sovichea.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-02T06:59:43.000Z","updated_at":"2026-01-07T17:17:48.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Sovichea/khmer_segmenter","commit_stats":null,"previous_names":["sovichea/khmer_segmenter"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Sovichea/khmer_segmenter","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sovichea%2Fkhmer_segmenter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sovichea%2Fkhmer_segmenter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sovichea%2Fkhmer_segmenter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sovichea%2Fkhmer_segmenter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Sovichea","download_url":"https://codeload.github.com/Sovichea/khmer_segmenter/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sovichea%2Fkhmer_segmenter/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28419272,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T10:47:48.104Z","status":"ssl_error","status_checked_at":"2026-01-14T10:46:19.031Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["c-language","dictionary-based","khmer","khmer-language","khmer-nlp","lightweight","nlp","portable","python","tokenization","viterbi-algorithm","word-segmentation","zero-dependency","zig-build-system"],"created_at":"2026-01-08T05:00:41.753Z","updated_at":"2026-01-14T12:00:33.441Z","avatar_url":"https://github.com/Sovichea.png","language":"Python","readme":null,"funding_links":[],"categories":["Awesome Khmer Language"],"sub_categories":["2. Toolkit"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FSovichea%2Fkhmer_segmenter","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FSovichea%2Fkhmer_segmenter","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FSovichea%2Fkhmer_segmenter/lists"}