{"id":15672933,"url":"https://github.com/erogol/tts_tf","last_synced_at":"2025-07-10T02:34:55.701Z","repository":{"id":145077822,"uuid":"215495114","full_name":"erogol/TTS_tf","owner":"erogol","description":"WIP Tensorflow implementation of https://github.com/mozilla/TTS","archived":false,"fork":false,"pushed_at":"2020-04-11T10:00:55.000Z","size":103,"stargazers_count":15,"open_issues_count":0,"forks_count":2,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-05-06T22:09:03.035Z","etag":null,"topics":["deep-learning","tacotron","tensorflow","tensorflow2","text-to-speech","tts"],"latest_commit_sha":null,"homepage":"","language":"Python","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/erogol.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":"2019-10-16T08:20:04.000Z","updated_at":"2023-03-19T20:16:58.000Z","dependencies_parsed_at":"2024-05-31T11:08:52.203Z","dependency_job_id":null,"html_url":"https://github.com/erogol/TTS_tf","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/erogol%2FTTS_tf","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2FTTS_tf/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2FTTS_tf/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2FTTS_tf/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/erogol","download_url":"https://codeload.github.com/erogol/TTS_tf/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252776601,"owners_count":21802469,"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":["deep-learning","tacotron","tensorflow","tensorflow2","text-to-speech","tts"],"created_at":"2024-10-03T15:33:48.933Z","updated_at":"2025-05-06T22:09:11.048Z","avatar_url":"https://github.com/erogol.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Tensorflow implementation of https://github.com/mozilla/TTS\n\n### TODO \n- [ ] Catching up with TTS pytorch\n    - [x] Replace pytorch layers with TF\n    - [x] Basic eager mode training \n        - 5x times slower than pytorch (if you see any easy optimizations, please let me know.)\n    - [ ] Optimization with tf.function\n        - tf.function looks so hard to use with models having different input shapes per iteration since TF retraces the graph for each input. As far as I see from the official examples, workarounds take the advantage of using eager mode. (Correct me if I am wrong.)\n    - [ ] TF based data loader\n\n- [ ] Model exporting pipeline for deployment\n- [ ] Vocoder adaptation\n    - [ ] WaveRNN\n    - [ ] LPCNet\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferogol%2Ftts_tf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ferogol%2Ftts_tf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferogol%2Ftts_tf/lists"}