{"id":17468443,"url":"https://github.com/egorsmkv/radtts-uk","last_synced_at":"2026-01-08T03:10:15.635Z","repository":{"id":166989026,"uuid":"642544332","full_name":"egorsmkv/radtts-uk","owner":"egorsmkv","description":"🇺🇦 Ukrainian RAD-TTS++ models (decoder + models with 3 voices) and HiFiGAN model","archived":false,"fork":false,"pushed_at":"2025-02-27T01:26:50.000Z","size":26,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-27T02:33:05.037Z","etag":null,"topics":["conversational-ai","hifigan","speech-ai","speech-synthesis","text-to-speech","tts","ukrainian","vocoder"],"latest_commit_sha":null,"homepage":"https://huggingface.co/Yehor/radtts-uk","language":null,"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/egorsmkv.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2023-05-18T20:13:20.000Z","updated_at":"2025-02-27T01:26:53.000Z","dependencies_parsed_at":"2023-05-29T02:00:26.010Z","dependency_job_id":null,"html_url":"https://github.com/egorsmkv/radtts-uk","commit_stats":null,"previous_names":["egorsmkv/radtts-uk"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/egorsmkv%2Fradtts-uk","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/egorsmkv%2Fradtts-uk/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/egorsmkv%2Fradtts-uk/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/egorsmkv%2Fradtts-uk/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/egorsmkv","download_url":"https://codeload.github.com/egorsmkv/radtts-uk/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246009029,"owners_count":20708880,"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":["conversational-ai","hifigan","speech-ai","speech-synthesis","text-to-speech","tts","ukrainian","vocoder"],"created_at":"2024-10-18T15:06:33.214Z","updated_at":"2026-01-08T03:10:15.594Z","avatar_url":"https://github.com/egorsmkv.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🇺🇦 Ukrainian RADTTS/RADTTS++ models and HiFiGAN model\n\nJoin our Speech Synthesis Group in Telegram: https://t.me/speech_synthesis_uk\n\nDonate: https://send.monobank.ua/jar/3Saxixsdua\n\n## Demo\n\nHugging Face space:\n\nhttps://huggingface.co/spaces/Yehor/radtts-uk-demo\n\n## Overview\n\nThis repository contains links to models:\n\n- Decoder model for RADTTS\n- Decoder model for RADTTS++\n- Pretrained model for RADTTS\n- Pretrained model for RADTTS++ with AGAP config\n- Pretrained model for RADTTS++ with BGAP config \n- Pretrained model for RADTTS++ with DAP config\n\nVoices are from [Open Source Ukrainian Text-to-Speech datasets](https://github.com/egorsmkv/ukrainian-tts-datasets)\n\nThese models have three voices:\n\n- Lada\n- Tetiana\n- Mykyta\n\n## Demo\n\n### Lada\n\nhttps://github.com/egorsmkv/radtts-uk/assets/7875085/ee89bc98-f425-4533-9404-5124ddc8e92c\n\n### Tetiana\n\nhttps://github.com/egorsmkv/radtts-uk/assets/7875085/88d29b0d-5f78-403d-be51-765444e53950\n\n### Mykyta\n\nhttps://github.com/egorsmkv/radtts-uk/assets/7875085/96d412b1-8977-48ed-93d0-6b741d6014ba\n\n## How to run?\n\nClone the repository https://github.com/egorsmkv/radtts and run the following command:\n\n```\npython inference.py -c config.json -r models/model_dap_84000.pt -v hifigan.pt -k hifigan_config.json \\\n  -t test.txt -s lada --speaker_attributes lada --speaker_text lada -o results\n```\n\n## Download\n\nDropbox link to all models: https://www.dropbox.com/scl/fo/0eoipxgk16o2cnw2ymba3/h?dl=0\u0026rlkey=7trclhuzuo6xno5n06xg4z7gd\n\n### Acknowledgement\n\n- Dmytro Chaplynskyi [@dchaplinsky](https://github.com/dchaplinsky): help with access to UCU's cluster\n- Decoder model for RADTTS++ and Pretrained model for RADTTS++ with DAP config have been trained on the Cluster of Excellence UCU/[Lang-uk](https://github.com/lang-uk).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fegorsmkv%2Fradtts-uk","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fegorsmkv%2Fradtts-uk","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fegorsmkv%2Fradtts-uk/lists"}