{"id":21343671,"url":"https://github.com/catalystcode/autocustomvocab","last_synced_at":"2025-10-12T20:16:04.116Z","repository":{"id":73516838,"uuid":"87110218","full_name":"CatalystCode/AutoCustomVocab","owner":"CatalystCode","description":"Automatically Generate Custom Vocabulary List for Microsoft Cognitive Services Custom Speech Service","archived":false,"fork":false,"pushed_at":"2017-04-04T17:18:49.000Z","size":9,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-01-22T15:47:59.885Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CatalystCode.png","metadata":{"files":{"readme":"README.md","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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-04-03T19:02:01.000Z","updated_at":"2017-04-03T19:10:41.000Z","dependencies_parsed_at":"2023-06-01T06:30:34.896Z","dependency_job_id":null,"html_url":"https://github.com/CatalystCode/AutoCustomVocab","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CatalystCode%2FAutoCustomVocab","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CatalystCode%2FAutoCustomVocab/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CatalystCode%2FAutoCustomVocab/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CatalystCode%2FAutoCustomVocab/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CatalystCode","download_url":"https://codeload.github.com/CatalystCode/AutoCustomVocab/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243818199,"owners_count":20352629,"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":"2024-11-22T01:14:40.704Z","updated_at":"2025-10-12T20:15:59.065Z","avatar_url":"https://github.com/CatalystCode.png","language":"R","readme":"# Automatically Generate Custom Vocabulary List for Microsoft Cognitive Services Custom Speech Service\n\nAutomatically generate a custom vocabulary list for Cognitive Services Custom Speech Service from your text corpus.\n\nThis R script allows you to quickly parse your text file of target text into single words and ngrams, compare these to lists of common words or ngrams, and generate a list of less frequent words and ngrams. You can review these less frequent words and ngrams, and generate your custom vocabulary list for training the Custom Speech Service\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcatalystcode%2Fautocustomvocab","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcatalystcode%2Fautocustomvocab","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcatalystcode%2Fautocustomvocab/lists"}