{"id":13423698,"url":"https://github.com/flashlight/wav2letter","last_synced_at":"2025-05-14T03:08:18.116Z","repository":{"id":39648149,"uuid":"111442748","full_name":"flashlight/wav2letter","owner":"flashlight","description":"Facebook AI Research's Automatic Speech Recognition Toolkit ","archived":false,"fork":false,"pushed_at":"2024-08-07T18:01:52.000Z","size":6501,"stargazers_count":6382,"open_issues_count":108,"forks_count":1012,"subscribers_count":246,"default_branch":"main","last_synced_at":"2024-10-29T15:05:17.926Z","etag":null,"topics":["cpp","deep-learning","end-to-end","speech-recognition","wav2letter"],"latest_commit_sha":null,"homepage":"https://github.com/facebookresearch/wav2letter/wiki","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/flashlight.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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":"2017-11-20T17:39:41.000Z","updated_at":"2024-10-27T13:34:24.000Z","dependencies_parsed_at":"2023-11-07T00:26:01.171Z","dependency_job_id":"65ada3c5-0f6c-4ecd-9ca3-76351f5c47df","html_url":"https://github.com/flashlight/wav2letter","commit_stats":null,"previous_names":["facebookresearch/wav2letter"],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flashlight%2Fwav2letter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flashlight%2Fwav2letter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flashlight%2Fwav2letter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flashlight%2Fwav2letter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/flashlight","download_url":"https://codeload.github.com/flashlight/wav2letter/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247962594,"owners_count":21024870,"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":["cpp","deep-learning","end-to-end","speech-recognition","wav2letter"],"created_at":"2024-07-31T00:00:40.861Z","updated_at":"2025-04-09T02:13:11.592Z","avatar_url":"https://github.com/flashlight.png","language":"C++","funding_links":[],"categories":["C++","\u003ca name=\"cpp\"\u003e\u003c/a\u003eC++","Natural Language Processing","🤖 AI \u0026 Machine Learning","Projects"],"sub_categories":["Speech \u0026 Audio"],"readme":"# wav2letter++\n\n[![CircleCI](https://circleci.com/gh/flashlight/wav2letter.svg?style=svg)](https://app.circleci.com/pipelines/github/flashlight/wav2letter)\n[![Join the chat at https://gitter.im/wav2letter/community](https://badges.gitter.im/wav2letter/community.svg)](https://gitter.im/wav2letter/community?utm_source=badge\u0026utm_medium=badge\u0026utm_campaign=pr-badge\u0026utm_content=badge)\n\n## Important Note:\n### wav2letter has been moved and consolidated [into Flashlight](https://github.com/flashlight/flashlight) in the [ASR application](https://github.com/flashlight/flashlight/tree/master/flashlight/app/asr).\n\nFuture wav2letter development will occur in Flashlight.\n\n*To build the old, pre-consolidation version of wav2letter*, checkout the [wav2letter v0.2](https://github.com/flashlight/wav2letter/releases/tag/v0.2) release, which depends on the old [Flashlight v0.2](https://github.com/flashlight/flashlight/releases/tag/v0.2) release. The [`wav2letter-lua`](https://github.com/flashlight/wav2letter/tree/wav2letter-lua) project can be found on the [`wav2letter-lua` branch](https://github.com/flashlight/wav2letter/tree/wav2letter-lua), accordingly.\n\nFor more information on wav2letter++, see or cite [this arXiv paper](https://arxiv.org/abs/1812.07625).\n\n## Recipes\nThis repository includes recipes to reproduce the following research papers as well as *pre-trained* models. **All results reproduction must use Flashlight \u003c= 0.3.2** for exact reproducability. Papers contained here include:\n- [Pratap et al. (2020): Scaling Online Speech Recognition Using ConvNets](recipes/streaming_convnets/)\n- [Synnaeve et al. (2020): End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures](recipes/sota/2019)\n- [Kahn et al. (2020): Self-Training for End-to-End Speech Recognition](recipes/self_training)\n- [Likhomanenko et al. (2019): Who Needs Words? Lexicon-free Speech Recognition](recipes/lexicon_free/)\n- [Hannun et al. (2019): Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions](recipes/seq2seq_tds/)\n\nData preparation for training and evaluation can be found in [data](data) directory.\n\n### Building the Recipes\n\nFirst, install [Flashlight](https://github.com/flashlight/flashlight/tree/0.3) **(using the [0.3 branch](https://github.com/flashlight/flashlight/tree/0.3) is required)** with the [ASR application](https://github.com/flashlight/flashlight/tree/master/flashlight/app/asr).\n```shell\nmkdir build \u0026\u0026 cd build\ncmake .. \u0026\u0026 make -j8\n```\nIf Flashlight or ArrayFire are installed in nonstandard paths via a custom `CMAKE_INSTALL_PREFIX`, they can be found by passing\n```shell\n-Dflashlight_DIR=[PREFIX]/usr/share/flashlight/cmake/ -DArrayFire_DIR=[PREFIX]/usr/share/ArrayFire/cmake\n```\nwhen running `cmake`.\n\n## Join the wav2letter community\n* Facebook page: https://www.facebook.com/groups/717232008481207/\n* Google group: https://groups.google.com/forum/#!forum/wav2letter-users\n* Contact: vineelkpratap@fb.com, awni@fb.com, qiantong@fb.com, jacobkahn@fb.com, antares@fb.com, avidov@fb.com, gab@fb.com, vitaliy888@fb.com, locronan@fb.com\n\n## License\nwav2letter++ is MIT-licensed, as found in the [LICENSE](LICENSE) file.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflashlight%2Fwav2letter","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fflashlight%2Fwav2letter","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflashlight%2Fwav2letter/lists"}