{"id":25963,"name":"noisy-sentences-dataset","description":"550K sentences in 5 European languages augmented with noise for training and evaluating spell correction tools or machine learning models.","url":"https://github.com/radi-cho/noisy-sentences-dataset","last_synced_at":"2025-09-05T03:00:36.899Z","repository":{"id":65668609,"uuid":"596943135","full_name":"radi-cho/noisy-sentences-dataset","owner":"radi-cho","description":"550K sentences in 5 European languages augmented with noise for training and evaluating spell correction tools or machine learning models.","archived":false,"fork":false,"pushed_at":"2023-02-03T10:11:20.000Z","size":8,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-13T12:16:48.185Z","etag":null,"topics":["dataset","natural-language-processing","nlp"],"latest_commit_sha":null,"homepage":"","language":null,"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/radi-cho.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-02-03T09:18:55.000Z","updated_at":"2023-03-24T18:09:30.000Z","dependencies_parsed_at":"2023-02-18T05:45:56.681Z","dependency_job_id":null,"html_url":"https://github.com/radi-cho/noisy-sentences-dataset","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/radi-cho/noisy-sentences-dataset","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radi-cho%2Fnoisy-sentences-dataset","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radi-cho%2Fnoisy-sentences-dataset/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radi-cho%2Fnoisy-sentences-dataset/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radi-cho%2Fnoisy-sentences-dataset/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/radi-cho","download_url":"https://codeload.github.com/radi-cho/noisy-sentences-dataset/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radi-cho%2Fnoisy-sentences-dataset/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273703685,"owners_count":25153003,"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","status":"online","status_checked_at":"2025-09-05T02:00:09.113Z","response_time":402,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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"}},"owner":{"login":"radi-cho","name":"Radi Cho","uuid":"12954909","kind":"user","description":"Student, 19. Machine Learning Research.","email":"","website":"https://www.linkedin.com/in/radostin-cholakov-bb4422146/","location":"Plovdiv, Bulgaria","twitter":"radi_cho","company":"Stanford University","icon_url":"https://avatars.githubusercontent.com/u/12954909?u=338d088598979a6e6e29232c222250c97c7d1584\u0026v=4","repositories_count":62,"last_synced_at":"2025-09-03T05:44:28.903Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/radi-cho","funding_links":[],"total_stars":2890,"followers":327,"following":26,"created_at":"2022-11-17T09:14:40.267Z","updated_at":"2025-09-03T05:44:28.903Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/radi-cho","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/radi-cho/repositories"},"packages":null,"commits":{"id":6818429,"full_name":"radi-cho/noisy-sentences-dataset","default_branch":"main","committers":[{"name":"Radi Cho","email":"12954909+radi-cho","login":"radi-cho","count":8}],"total_commits":8,"total_committers":1,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":8.0,"dds":0.0,"past_year_committers":[],"past_year_total_commits":0,"past_year_total_committers":0,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":0.0,"past_year_dds":0.0,"last_synced_at":"2025-01-02T11:31:38.486Z","last_synced_commit":"182bb0964b85b643d0227acfb6bb21dfa4e1f8ff","created_at":"2024-11-25T10:48:47.760Z","updated_at":"2025-01-02T11:31:38.486Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/radi-cho%2Fnoisy-sentences-dataset/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.343Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"radi-cho/noisy-sentences-dataset","html_url":"https://github.com/radi-cho/noisy-sentences-dataset","last_synced_at":"2025-03-20T06:24:54.854Z","status":null,"issues_count":0,"pull_requests_count":0,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":0,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":0,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2024-11-25T10:48:48.339Z","updated_at":"2025-03-20T06:24:54.854Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/radi-cho%2Fnoisy-sentences-dataset","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/radi-cho%2Fnoisy-sentences-dataset/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{},"issue_authors":{},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.444Z","repositories_count":10083752,"issues_count":31254324,"pull_requests_count":96222393,"authors_count":10694625,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{},"last_year":{}},"keywords":["dataset","natural-language-processing","nlp"],"dependencies":[],"score":0.6931471805599453,"created_at":"2025-09-04T15:50:58.002Z","updated_at":"2025-10-07T08:11:44.732Z","avatar_url":"https://github.com/radi-cho.png","language":null,"category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/25963","html_url":"https://science.ecosyste.ms/projects/25963","bibtex_url":"https://science.ecosyste.ms/projects/25963/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/25963/export.apalike"}