{"id":28802706,"url":"https://github.com/ryanfb/latinocr-lattraining","last_synced_at":"2026-02-03T17:02:20.451Z","repository":{"id":23607312,"uuid":"26976332","full_name":"ryanfb/latinocr-lattraining","owner":"ryanfb","description":"Rules and tools to deterministically generate all prerequisites for the final training process. Adapted from https://github.com/ryanfb/ancientgreekocr-grctraining/","archived":false,"fork":false,"pushed_at":"2016-01-13T15:57:53.000Z","size":16058,"stargazers_count":6,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2023-04-11T17:41:04.159Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Makefile","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ryanfb.png","metadata":{"files":{"readme":"README","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}},"created_at":"2014-11-21T20:17:52.000Z","updated_at":"2022-06-28T20:10:47.000Z","dependencies_parsed_at":"2022-08-22T01:30:56.142Z","dependency_job_id":null,"html_url":"https://github.com/ryanfb/latinocr-lattraining","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"purl":"pkg:github/ryanfb/latinocr-lattraining","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryanfb%2Flatinocr-lattraining","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryanfb%2Flatinocr-lattraining/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryanfb%2Flatinocr-lattraining/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryanfb%2Flatinocr-lattraining/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ryanfb","download_url":"https://codeload.github.com/ryanfb/latinocr-lattraining/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryanfb%2Flatinocr-lattraining/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260515089,"owners_count":23020618,"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":[],"created_at":"2025-06-18T08:07:22.701Z","updated_at":"2026-02-03T17:02:20.446Z","avatar_url":"https://github.com/ryanfb.png","language":"Makefile","funding_links":[],"categories":[],"sub_categories":[],"readme":"Source files for some automatically generated parts of the\nLatin (lat) training for Tesseract OCR. Specifically, this contains\nthe Makefile and its prerequisites to build the following files\nneeded for the lat training:\n\n- training_text.txt\n- lat.word.txt\n- lat.freq.txt\n- lat.unicharambigs\n- lat.wordlist\n\n\n# Dependencies\n\nOn a Mac with homebrew, install coreutils and gnu-sed (needed for\ngsed, gmktemp, gshuf).\n\n# To build the training parts\n\nNote that the build starts by downloading and unpacking a text\ncorpus from which to generate the wordlists.\n\nMake all of the parts with the command:\n  make\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryanfb%2Flatinocr-lattraining","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fryanfb%2Flatinocr-lattraining","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryanfb%2Flatinocr-lattraining/lists"}