{"id":19695843,"url":"https://github.com/wenet-e2e/wetts","last_synced_at":"2025-04-05T20:06:10.969Z","repository":{"id":37085899,"uuid":"461062846","full_name":"wenet-e2e/wetts","owner":"wenet-e2e","description":"Production First and Production Ready End-to-End Text-to-Speech Toolkit","archived":false,"fork":false,"pushed_at":"2024-05-30T05:34:34.000Z","size":3594,"stargazers_count":384,"open_issues_count":24,"forks_count":59,"subscribers_count":15,"default_branch":"main","last_synced_at":"2025-03-29T06:51:34.601Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/wenet-e2e.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":"2022-02-19T02:09:40.000Z","updated_at":"2025-03-24T05:44:14.000Z","dependencies_parsed_at":"2025-01-27T10:07:57.724Z","dependency_job_id":"db8d91e0-ae6c-4ba1-9416-cbf845f80ef3","html_url":"https://github.com/wenet-e2e/wetts","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/wenet-e2e%2Fwetts","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wenet-e2e%2Fwetts/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wenet-e2e%2Fwetts/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wenet-e2e%2Fwetts/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wenet-e2e","download_url":"https://codeload.github.com/wenet-e2e/wetts/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247393568,"owners_count":20931812,"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":"2024-11-11T19:31:07.772Z","updated_at":"2025-04-05T20:06:10.945Z","avatar_url":"https://github.com/wenet-e2e.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# WeTTS\n\nProduction First and Production Ready End-to-End Text-to-Speech Toolkit\n\n## Install\n\n### Install python package\n``` sh\npip install git+https://github.com/wenet-e2e/wetts.git\n```\n**Command-line usage** (use `-h` for parameters):\n\n``` sh\nwetts --text \"今天天气怎么样\" --wav output.wav\n```\n\n**Python programming usage**:\n\n``` python\nimport wetts\n\n# TODO\n```\n\n### Install for development \u0026 deployment\n\nWe suggest to install WeTTS with Anaconda or Miniconda.\n\nClone this repo:\n\n```sh\ngit clone https://github.com/wenet-e2e/wetts.git\n```\n\nCreate the environment:\n\n```bash\nconda create -n wetts python=3.8 -y\nconda activate wetts\npip install -r requirements.txt\n```\n\n## Roadmap\n\nWe mainly focus on end to end, production, and on-device TTS. We are going to use:\n\n* backend: end to end model, such as:\n  * [VITS](https://arxiv.org/pdf/2106.06103.pdf)\n* frontend:\n  * Text Normalization: [WeTextProcessing](https://github.com/wenet-e2e/WeTextProcessing)\n  * Prosody \u0026 Polyphones: [Unified Mandarin TTS Front-end Based on Distilled BERT Model](https://arxiv.org/pdf/2012.15404.pdf)\n\n## Dataset\n\nWe plan to support a variaty of open source TTS datasets, include but not limited to:\n\n* [Baker](https://www.data-baker.com/data/index/TNtts), Chinese Standard Mandarin Speech corpus open sourced by Data Baker.\n* [AISHELL-3](https://openslr.org/93), a large-scale and high-fidelity multi-speaker Mandarin speech corpus.\n* [Opencpop](https://wenet.org.cn/opencpop), Mandarin singing voice synthesis (SVS) corpus open sourced by Netease Fuxi.\n\n## Pretrained Models\n\n| Dataset        | Language | Checkpoint Model | Runtime Model |\n| -------------- | -------- | ---------------- | ------------- |\n| Baker          | CN       | [BERT](https://wenet.org.cn/downloads?models=wetts\u0026version=baker_bert_exp.tar.gz) | [BERT](https://wenet.org.cn/downloads?models=wetts\u0026version=baker_bert_onnx.tar.gz) |\n| Multilingual   | CN       | [VITS](https://wenet.org.cn/downloads?models=wetts\u0026version=multilingual_vits_v3_exp.tar.gz) | [VITS](https://wenet.org.cn/downloads?models=wetts\u0026version=multilingual_vits_v3_onnx.tar.gz) |\n\n## Runtime\n\nWe plan to support a variaty of hardwares and platforms, including:\n\n* x86\n* Android\n* Raspberry Pi\n* Other on-device platforms\n\n``` bash\nexport GLOG_logtostderr=1\nexport GLOG_v=2\n\ncd runtime/onnxruntime\ncmake -B build -DCMAKE_BUILD_TYPE=Release\ncmake --build build\n./build/bin/tts_main \\\n  --frontend_flags baker_bert_onnx/frontend.flags \\\n  --vits_flags multilingual_vits_v3_onnx/vits.flags \\\n  --sname baker \\\n  --text \"hello我是小明。\" \\\n  --wav_path audio.wav\n```\n\n## Discussion \u0026 Communication\n\nFor Chinese users, you can aslo scan the QR code on the left to follow our offical account of WeNet.\nWe created a WeChat group for better discussion and quicker response.\nPlease scan the personal QR code on the right, and the guy is responsible for inviting you to the chat group.\n\n| \u003cimg src=\"https://github.com/robin1001/qr/blob/master/wenet.jpeg\" width=\"250px\"\u003e | \u003cimg src=\"https://github.com/pengzhendong/files/blob/master/images/wechat.png\" width=\"250px\"\u003e |\n| ---- | ---- |\n\nOr you can directly discuss on [Github Issues](https://github.com/wenet-e2e/wetts/issues).\n\n## Acknowledgement\n\n1. We borrow a lot of code from [vits](https://github.com/jaywalnut310/vits) for VITS implementation.\n2. We refer [PaddleSpeech](https://github.com/PaddlePaddle/PaddleSpeech) for `pinyin` lexicon generation.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwenet-e2e%2Fwetts","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwenet-e2e%2Fwetts","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwenet-e2e%2Fwetts/lists"}