{"id":17816981,"url":"https://github.com/thewh1teagle/israwave","last_synced_at":"2025-04-10T01:08:32.683Z","repository":{"id":245502128,"uuid":"818441336","full_name":"thewh1teagle/israwave","owner":"thewh1teagle","description":"Mission to create a Hebrew TTS model as powerful and user-friendly as WaveNet","archived":false,"fork":false,"pushed_at":"2025-01-05T04:24:20.000Z","size":182,"stargazers_count":33,"open_issues_count":7,"forks_count":8,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-04-10T01:08:25.830Z","etag":null,"topics":["hebrew","israel","pytorch","tts"],"latest_commit_sha":null,"homepage":"https://huggingface.co/spaces/thewh1teagle/tts-with-israwave","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/thewh1teagle.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":"2024-06-21T21:37:05.000Z","updated_at":"2025-03-03T19:07:25.000Z","dependencies_parsed_at":"2024-06-22T13:03:42.585Z","dependency_job_id":"a01f515a-0b2c-452a-ad87-e7f542867679","html_url":"https://github.com/thewh1teagle/israwave","commit_stats":null,"previous_names":["thewh1teagle/israwave"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thewh1teagle%2Fisrawave","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thewh1teagle%2Fisrawave/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thewh1teagle%2Fisrawave/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thewh1teagle%2Fisrawave/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thewh1teagle","download_url":"https://codeload.github.com/thewh1teagle/israwave/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248137887,"owners_count":21053775,"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":["hebrew","israel","pytorch","tts"],"created_at":"2024-10-27T16:39:59.077Z","updated_at":"2025-04-10T01:08:32.662Z","avatar_url":"https://github.com/thewh1teagle.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# israwave\n\nMission to create a Hebrew TTS model as powerful and user-friendly as WaveNet\n\n## Features\n\n- Generate sentence in less than 1ms on CPU\n- Powerful text processor by espeak-ng\n- Support for SSML (soon)\n\n## Play with it!\n\nYou can play with it on [HuggingFace Space](https://huggingface.co/spaces/thewh1teagle/tts-with-israwave)\n\n## Samples\n\nhttps://github.com/user-attachments/assets/3212a800-406f-4d79-8aa1-d814eed815d6\n\n## Setup\n\n```console\npip install -U israwave\n```\n\n- You also need to place the files [`israwave.onnx`](https://github.com/thewh1teagle/israwave/releases/download/v0.1.0/israwave.onnx), [`nakdimon.onnx`](https://github.com/thewh1teagle/israwave/releases/download/v0.1.0/nakdimon.onnx), and extracted [`espeak-ng-data`](https://github.com/thewh1teagle/israwave/releases/download/v0.1.0/espeak-ng-data.tar.gz) in the project folder. \n- We recommend use [uv](https://docs.astral.sh/uv/getting-started/installation) for Python.\n- Python 3.12 is recommended. (`uv init -p 3.12`)\n- Please see examples.\n\n## Examples\n\nSee [examples](examples)\n\n## Dataset\n\nThe model trained on [saspeech gold standard](https://openslr.org/134/).\n\n## Thanks\n\nThanks to [Kan11](https://www.kan.org.il/) and [Shaul](https://www.kan.org.il/authors/%D7%A9%D7%90%D7%95%D7%9C-%D7%90%D7%9E%D7%A1%D7%98%D7%A8%D7%93%D7%9E%D7%A1%D7%A7%D7%99/) for providing the dataset.\n\nThanks to [elazarg](https://github.com/elazarg) for sharing the [Nakdimon](https://github.com/elazarg/nakdimon) diacritics model, which was instrumental in our project.\n\nFor [mush42](https://github.com/mush42) for their excellent TTS training recipe.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthewh1teagle%2Fisrawave","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthewh1teagle%2Fisrawave","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthewh1teagle%2Fisrawave/lists"}