{"id":19695827,"url":"https://github.com/wenet-e2e/west","last_synced_at":"2026-01-21T19:41:34.314Z","repository":{"id":332281245,"uuid":"1001300675","full_name":"wenet-e2e/west","owner":"wenet-e2e","description":"We Speech Toolkit,  LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction","archived":false,"fork":false,"pushed_at":"2026-01-13T06:14:10.000Z","size":2275,"stargazers_count":173,"open_issues_count":13,"forks_count":13,"subscribers_count":8,"default_branch":"main","last_synced_at":"2026-01-13T09:31:14.928Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-06-13T06:40:25.000Z","updated_at":"2026-01-13T06:14:14.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/wenet-e2e/west","commit_stats":null,"previous_names":["wenet-e2e/west"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/wenet-e2e/west","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wenet-e2e%2Fwest","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wenet-e2e%2Fwest/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wenet-e2e%2Fwest/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wenet-e2e%2Fwest/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wenet-e2e","download_url":"https://codeload.github.com/wenet-e2e/west/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wenet-e2e%2Fwest/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28641279,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-21T18:04:35.752Z","status":"ssl_error","status_checked_at":"2026-01-21T18:03:55.054Z","response_time":86,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":"2024-11-11T19:31:03.701Z","updated_at":"2026-01-21T19:41:34.308Z","avatar_url":"https://github.com/wenet-e2e.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# WEST\n\n[![License](https://img.shields.io/badge/License-Apache%202.0-brightgreen.svg)](https://opensource.org/licenses/Apache-2.0)\n[![Docs](https://img.shields.io/badge/Docs-latest-brightgreen.svg)](docs/)\n[![Paper](https://img.shields.io/badge/Paper-arXiv-f9f107.svg)](https://arxiv.org/abs/2509.19902)\n[![WeChat](https://img.shields.io/badge/WeChat-07C160?style=flat\u0026logo=wechat\u0026logoColor=white)](#discussion--communication)\n\n\n**We** **S**peech **T**ookit, LLM based Speech Toolkit for Speech Understanding,\nGeneration, and Interaction.\n\n## Highlights\n\n* **Fully LLM-based**: Standing on the shoulders of giants by reusing mature\n  architectures, ecosystems (e.g., Hugging Face), and methods (e.g.,\n  sequence packing) from large models.\n* **Full-stack**: Supports tasks such as recognition, synthesis, understanding,\n  dialogue, and multimodal capabilities, with extensibility to incorporate\n  open-source models.\n\n* **Simple and Stupid**: A simple and stupid speech toolkit that\n  everyone can Touch.\n\n## Install\n\n``` bash\nconda create -n west python=3.10\nconda activate west\npip install -r requirements.txt\n```\n\n## Supported Tasks and Models\n\n| Task                   | Model               | Recipe                                                                  |\n|------------------------|---------------------|-------------------------------------------------------------------------|\n| Speech Recognition     | TouchASU(Built-in)  | [aishell](examples/aishell/asr)                                         |\n| Speech Synthesis       | TouchTTS(Built-in)  | [libritts](examples/libritts/tts)                                       |\n| Speech QA              | TouchASU(Built-in)  | [belle_1.4M_qa](examples/belle_1.4M_qa)                                 |\n| Speech Interaction     | TouchChat(Built-in) |                                                                         |\n| MutliModal Interaction | TouchOmni(Built-in) |                                                                         |\n\n\n## Citation\n\nOur paper is available on [arXiv](https://arxiv.org/abs/2509.19902), and you can cite it as:\n\n```\n@misc{zhang2025westllmbasedspeech,\n      title={WEST: LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction},\n      author={Binbin Zhang and Chengdong Liang and Shuai Wang and Xuelong Geng and Zhao Guo and Haoyu Li and Hao Yin and Xipeng Yang and Pengshen Zhang and Changwei Ma and Lei Xie},\n      year={2025},\n      eprint={2509.19902},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2509.19902},\n}\n```\n\n## Discussion \u0026 Communication\n\nWe created a WeChat group for better discussion and quicker response.\nPlease scan the personal QR code on the left, who is responsible for inviting you to the chat group.\nYou can also scan the QR code on the right to follow our official account of WeNet Community.\n\n| \u003cimg src=\"https://raw.githubusercontent.com/robin1001/qr/master/chengdong.jpg\" width=\"250px\"\u003e | \u003cimg src=\"https://raw.githubusercontent.com/robin1001/qr/master/wenet.jpeg\" width=\"250px\"\u003e |\n| ---- | ---- |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwenet-e2e%2Fwest","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwenet-e2e%2Fwest","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwenet-e2e%2Fwest/lists"}