{"id":25865280,"url":"https://github.com/jcaperella29/document_cleaning_cli","last_synced_at":"2026-06-08T04:32:20.250Z","repository":{"id":277746591,"uuid":"933370582","full_name":"jcaperella29/Document_cleaning_CLI","owner":"jcaperella29","description":"🧠 AI-powered pipeline for cleaning scanned documents. Removes noise, enhances text, auto-tunes model weights, and returns OCR-optimized PDFs via CLI or cloud API.","archived":false,"fork":false,"pushed_at":"2026-05-26T23:30:27.000Z","size":99257,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-05-27T01:20:15.103Z","etag":null,"topics":["auto-tune","batch-processing","cli-tool","cloud-run","computer-vision","deep-learning","denoising","document-ai","document-processing","fastapi","image-enhancement","image-processing","ocr","ocr-pipeline","ocr-pipelines","pytesseract","python","rest-api","scanned-documents"],"latest_commit_sha":null,"homepage":"https://document-cleaning-cli-111-777-888-7777-934773375188.us-central1.run.app/","language":"MATLAB","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jcaperella29.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-02-15T19:43:33.000Z","updated_at":"2026-05-26T23:30:31.000Z","dependencies_parsed_at":null,"dependency_job_id":"2138c22e-66e3-4f4b-861c-112e441e9045","html_url":"https://github.com/jcaperella29/Document_cleaning_CLI","commit_stats":null,"previous_names":["jcaperella29/document_cleaning_cli"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jcaperella29/Document_cleaning_CLI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jcaperella29%2FDocument_cleaning_CLI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jcaperella29%2FDocument_cleaning_CLI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jcaperella29%2FDocument_cleaning_CLI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jcaperella29%2FDocument_cleaning_CLI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jcaperella29","download_url":"https://codeload.github.com/jcaperella29/Document_cleaning_CLI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jcaperella29%2FDocument_cleaning_CLI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34048681,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-08T02:00:07.615Z","response_time":111,"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"}},"keywords":["auto-tune","batch-processing","cli-tool","cloud-run","computer-vision","deep-learning","denoising","document-ai","document-processing","fastapi","image-enhancement","image-processing","ocr","ocr-pipeline","ocr-pipelines","pytesseract","python","rest-api","scanned-documents"],"created_at":"2025-03-02T01:34:14.058Z","updated_at":"2026-06-08T04:32:20.231Z","avatar_url":"https://github.com/jcaperella29.png","language":"MATLAB","funding_links":[],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjcaperella29%2Fdocument_cleaning_cli","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjcaperella29%2Fdocument_cleaning_cli","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjcaperella29%2Fdocument_cleaning_cli/lists"}