{"id":18439582,"url":"https://github.com/idiap/asrt","last_synced_at":"2025-07-31T09:09:44.609Z","repository":{"id":31904636,"uuid":"35473679","full_name":"idiap/asrt","owner":"idiap","description":"Various scripts that facilitate the preparation of Automatic Speech Recognition related resources","archived":false,"fork":false,"pushed_at":"2020-04-16T10:39:23.000Z","size":4303,"stargazers_count":17,"open_issues_count":1,"forks_count":7,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-04-07T21:41:31.558Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/idiap.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"COPYING","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2015-05-12T07:32:01.000Z","updated_at":"2024-04-29T02:01:20.000Z","dependencies_parsed_at":"2022-08-28T21:23:50.150Z","dependency_job_id":null,"html_url":"https://github.com/idiap/asrt","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/idiap/asrt","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fasrt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fasrt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fasrt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fasrt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/idiap","download_url":"https://codeload.github.com/idiap/asrt/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fasrt/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268016887,"owners_count":24181656,"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":"2025-07-31T02:00:08.723Z","response_time":66,"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":[],"created_at":"2024-11-06T06:25:36.689Z","updated_at":"2025-07-31T09:09:44.554Z","avatar_url":"https://github.com/idiap.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"README\n======\nAuthors\n-------\nAlexandre Nanchen, Christine Marcel\n\nDescription\n-----------\nThis is the README for the Automatic Speech Recognition Tools.\n\nThis project contains various scripts in order to facilitate the preparation of\nASR related tasks.\n\nCurrent tasks are:\n\n1. Sentences extraction from pdf files\n2. Sentences classification by language\n3. Sentences filtering and cleaning\n\nDocument sentences can be extracted into single document or batch mode.\n\nFor an example on how to extract sentences in batch mode, please have a\nlook at the `run_data_preparation_task.sh` script located in\n`examples/bash` directory.\n\nFor an example on how to extract sentences in single document mode,\nplease have a look at the `run_data_preparation.sh` script located in\n`examples/bash` directory.\n\nThere is also an API to be used in python code. It is located into the\ncommon package and is called `DataPreparationAPI.py`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidiap%2Fasrt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fidiap%2Fasrt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidiap%2Fasrt/lists"}