{"id":21965699,"url":"https://github.com/styts/speech","last_synced_at":"2025-03-22T21:33:33.025Z","repository":{"id":147302430,"uuid":"91385193","full_name":"styts/speech","owner":"styts","description":"A study in speech recognition in Clojure","archived":false,"fork":false,"pushed_at":"2017-05-15T21:11:26.000Z","size":895,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-28T01:26:59.805Z","etag":null,"topics":["clojure","fft","machine-learning","spectrogram","speech-recognition"],"latest_commit_sha":null,"homepage":null,"language":"Clojure","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/styts.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":"2017-05-15T21:10:44.000Z","updated_at":"2024-05-20T11:57:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"279a4675-6eb9-4228-bd08-4d05c393ef7e","html_url":"https://github.com/styts/speech","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/styts%2Fspeech","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/styts%2Fspeech/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/styts%2Fspeech/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/styts%2Fspeech/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/styts","download_url":"https://codeload.github.com/styts/speech/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245022962,"owners_count":20548629,"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":["clojure","fft","machine-learning","spectrogram","speech-recognition"],"created_at":"2024-11-29T12:50:12.317Z","updated_at":"2025-03-22T21:33:32.969Z","avatar_url":"https://github.com/styts.png","language":"Clojure","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Speech\n\nAn app that can currently visualize live audio data from the microphone, but\naspires to be more one day (speech recognition is hard!).\n\n![](resources/demo.gif)\n\n## Roadmap\nPhase 0: Capture and display audio data\n\n* [x] capture live microphone data\n* [x] display live audio data as graph the browser\n* [x] display live spectrogram (it's not as good as I'd like)\n* [x] signal windowing before spectrogram\n* [x] find ways to normalize fft results\n\n-----\n\nPhase 1: ML\n\n* [ ] train neural network to detect presence of speech in audio samples\n* [ ] send identified speech sample to Google for recognition\n* [ ] alternatively do phoneme detection locally\n* [ ] configurable utterance to function mapping (e.g. \"next bus\" or \"weather tomorrow\")\n\n## Development workflow\n\nStart the cljs/css watching process and open http://localhost:3000 with:\n\n    boot frontend\n\nConnect to a Clojure repl, open `user.clj` and run this code to start the\nwebserver and microphone capture components:\n\n    (set-init! #'dev-system)\n    (reset)\n\nYou should see a graph of live microphone data coming in through the websocket.\n\nIf you now call `(snd)`, you can display the current frame, the frame with the\nhamming-window applied and the power spectrum (later being the same data as\ncolumns in the spectrogram) as charts in the browser.\n\n## TODOs\n* [ ] add gif animation to readme\n* [ ] refactor `app.cljs` to use multimethods for dispatching the message handler\n* [ ] moves styles to the frontend\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstyts%2Fspeech","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fstyts%2Fspeech","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstyts%2Fspeech/lists"}