{"id":13490700,"url":"https://github.com/GermanT5/wikipedia2corpus","last_synced_at":"2025-03-28T06:31:45.047Z","repository":{"id":50352288,"uuid":"461587897","full_name":"GermanT5/wikipedia2corpus","owner":"GermanT5","description":"Wikipedia text corpus for self-supervised NLP model training","archived":false,"fork":false,"pushed_at":"2022-07-17T07:25:32.000Z","size":51,"stargazers_count":40,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-10-31T04:34:52.802Z","etag":null,"topics":["corpus","german-nlp","machine-learning","nlp","somajo","wikipedia","wikipedia-corpus"],"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/GermanT5.png","metadata":{},"created_at":"2022-02-20T19:05:24.000Z","updated_at":"2024-10-21T19:47:46.000Z","dependencies_parsed_at":"2022-08-23T09:50:07.071Z","dependency_job_id":null,"html_url":"https://github.com/GermanT5/wikipedia2corpus","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GermanT5%2Fwikipedia2corpus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GermanT5%2Fwikipedia2corpus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GermanT5%2Fwikipedia2corpus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GermanT5%2Fwikipedia2corpus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GermanT5","download_url":"https://codeload.github.com/GermanT5/wikipedia2corpus/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245984581,"owners_count":20704793,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["corpus","german-nlp","machine-learning","nlp","somajo","wikipedia","wikipedia-corpus"],"created_at":"2024-07-31T19:00:50.238Z","updated_at":"2025-03-28T06:31:45.039Z","avatar_url":"https://github.com/GermanT5.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FGermanT5%2Fwikipedia2corpus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FGermanT5%2Fwikipedia2corpus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FGermanT5%2Fwikipedia2corpus/lists"}