{"id":21298825,"url":"https://github.com/litee/tts-asr-corpora","last_synced_at":"2026-01-03T00:14:17.195Z","repository":{"id":87649225,"uuid":"142709239","full_name":"Litee/tts-asr-corpora","owner":"Litee","description":"Catalogue of TTS and ASR corpora that can be used for machine learning","archived":false,"fork":false,"pushed_at":"2018-07-28T21:34:54.000Z","size":2,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-22T07:37:16.217Z","etag":null,"topics":["asr","corpora","corpus","corpus-linguistics","machine-learning","text-to-speech","tts"],"latest_commit_sha":null,"homepage":"","language":null,"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/Litee.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}},"created_at":"2018-07-28T20:49:41.000Z","updated_at":"2021-11-03T04:03:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"6a2aa3db-53b5-4d4d-8776-fdbbe9b214b7","html_url":"https://github.com/Litee/tts-asr-corpora","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/Litee%2Ftts-asr-corpora","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Litee%2Ftts-asr-corpora/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Litee%2Ftts-asr-corpora/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Litee%2Ftts-asr-corpora/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Litee","download_url":"https://codeload.github.com/Litee/tts-asr-corpora/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243769947,"owners_count":20345215,"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":["asr","corpora","corpus","corpus-linguistics","machine-learning","text-to-speech","tts"],"created_at":"2024-11-21T14:57:38.201Z","updated_at":"2026-01-03T00:14:17.162Z","avatar_url":"https://github.com/Litee.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Text-To-Speech and Automatic Speech Recognition Corpora\n\nCorpus | Languages/Voices | Audio Length | Download Size | URL\n--- | --- | --- | --- | ---\nCMU Arctic | 4 clean US English, 3 accented | 1150 clips | 100-150 Mb per voice | [Here](http://festvox.org/cmu_arctic/)\nCSTR VCTK | 109 English voices | 400 sentences per speaker | 10.5 Gb | [Here](http://homepages.inf.ed.ac.uk/jyamagis/page3/page58/page58.html)\nLJSpeech | One English voice | 13,100 clips | 2.6 Gb | [Here](https://keithito.com/LJ-Speech-Dataset/)\nTEDLIUM | Multiple English voices | 452 hours | 50 Gb | [Here](https://lium.univ-lemans.fr/en/ted-lium3/)\nM-AILABS | German, US/UK English, Spanish, Italian, Russian, etc | 999 hours | 110 Gb | [Here](http://www.m-ailabs.bayern/en/the-mailabs-speech-dataset/)\nLibriSpeech | Multiple English voices | 1000 hours | 60 Gb | [Here](http://www.openslr.org/12/)\nThe World English Bible | One English voice | ??? | 5 Gb | [Here](https://www.kaggle.com/bryanpark/the-world-english-bible-speech-dataset)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flitee%2Ftts-asr-corpora","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flitee%2Ftts-asr-corpora","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flitee%2Ftts-asr-corpora/lists"}