{"id":23075080,"url":"https://github.com/sk-g/speech-recognition-tensorflow-challenge","last_synced_at":"2025-08-14T00:10:18.912Z","repository":{"id":80507162,"uuid":"114806388","full_name":"sk-g/Speech-Recognition-Tensorflow-Challenge","owner":"sk-g","description":"Different CNN Models for keyword spotting in speech recognition","archived":false,"fork":false,"pushed_at":"2018-07-11T23:38:08.000Z","size":1335676,"stargazers_count":10,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-04-03T18:13:03.842Z","etag":null,"topics":["alexnet-model","cnn","deep-learning","machine-learning","neural-networks","speech-recognition","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sk-g.png","metadata":{"files":{"readme":"ReadMe","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":"2017-12-19T20:05:52.000Z","updated_at":"2020-12-21T07:36:59.000Z","dependencies_parsed_at":null,"dependency_job_id":"a094e0e1-8bac-4fb0-aecf-86f6834236f7","html_url":"https://github.com/sk-g/Speech-Recognition-Tensorflow-Challenge","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sk-g/Speech-Recognition-Tensorflow-Challenge","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sk-g%2FSpeech-Recognition-Tensorflow-Challenge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sk-g%2FSpeech-Recognition-Tensorflow-Challenge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sk-g%2FSpeech-Recognition-Tensorflow-Challenge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sk-g%2FSpeech-Recognition-Tensorflow-Challenge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sk-g","download_url":"https://codeload.github.com/sk-g/Speech-Recognition-Tensorflow-Challenge/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sk-g%2FSpeech-Recognition-Tensorflow-Challenge/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270336745,"owners_count":24566795,"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","status":"online","status_checked_at":"2025-08-13T02:00:09.904Z","response_time":66,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["alexnet-model","cnn","deep-learning","machine-learning","neural-networks","speech-recognition","tensorflow"],"created_at":"2024-12-16T08:38:43.154Z","updated_at":"2025-08-14T00:10:18.722Z","avatar_url":"https://github.com/sk-g.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"### Update 10/07/2018\n\n## MAJOR CHANGES COMING IN SOON, inlcuding pytorch implementation and better structure\n\nTensorflow Speech Recognition Challenge\nhttps://www.kaggle.com/c/tensorflow-speech-recognition-challenge\nFolders : \n\timages: audio clips -\u003e spectrogram images \n\tim_train: -\u003e images -\u003e resize to 28x28\n\tresults: results in graphs\n\tpapers: some useful papers\n\ttest_pics : ignore (spectrograms of test audio clips)\n\tDeprecated : old GCP files. Ignore\nFiles :\n\tcomplete.py -\u003e code with two CNN models and adversarial training\n\tReadMe -\u003e this\n\n\tSome files were used for preprocessing on older data\n\tbut maybe useful for other projects\n\tignore these:\n\t\tCNN_code_for_resized_data.py\n\t\tdataset.py\n\t\tdownsizing.py \u003c- recursively resize all images in a folder\n\t\tds.py \u003c- tried an iterator\n\t\tpp.py \u003c- audio to image conversion. recursively converts all audio clips in a folder to \n\t\t\t\t corresponding spectrograms\n\t\tspeech_recog.py \u003c- ignore\n\t\tGCP-SR.py \u003c-- for local usage in google cloud platform\n\t\t\n\nModels:\nShallow CNN: CNN similar to AlexNet. Two fc layers at the end, dropout enabled/disabled.\n\nDeeper CNN:\n\twide  : added more layers to the CNN, removed dropout\n\twider : increased number of filters\n\n\nFor Results and Talks:\n\tML_final.pdf\n\tML_talk.pdf\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsk-g%2Fspeech-recognition-tensorflow-challenge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsk-g%2Fspeech-recognition-tensorflow-challenge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsk-g%2Fspeech-recognition-tensorflow-challenge/lists"}