{"id":24684909,"url":"https://github.com/zvikinoza/masr","last_synced_at":"2025-03-21T20:40:28.278Z","repository":{"id":241247771,"uuid":"231761639","full_name":"zvikinoza/MASR","owner":"zvikinoza","description":"Mini Automatic Speech Recognition","archived":false,"fork":false,"pushed_at":"2022-09-26T19:29:50.000Z","size":88200,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-26T15:16:56.561Z","etag":null,"topics":["fourier-transform","keras-tensorflow","librosa","sound-processing","speech-recognition","speech-to-text"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/zvikinoza.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":"2020-01-04T12:45:50.000Z","updated_at":"2022-09-26T19:29:54.000Z","dependencies_parsed_at":"2024-05-23T05:26:07.307Z","dependency_job_id":null,"html_url":"https://github.com/zvikinoza/MASR","commit_stats":null,"previous_names":["zvikinoza/masr"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zvikinoza%2FMASR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zvikinoza%2FMASR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zvikinoza%2FMASR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zvikinoza%2FMASR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zvikinoza","download_url":"https://codeload.github.com/zvikinoza/MASR/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244867992,"owners_count":20523581,"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":["fourier-transform","keras-tensorflow","librosa","sound-processing","speech-recognition","speech-to-text"],"created_at":"2025-01-26T15:17:03.105Z","updated_at":"2025-03-21T20:40:28.259Z","avatar_url":"https://github.com/zvikinoza.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Mini Automatic Speech Recognition \n## Using Fourier transforms and CNN (VGG like) architecture\n\n![ ](https://github.com/zvikiNozadze/MASR/blob/master/imgs/number_spectogram.png)\n\nEDA and modeling on ≈150 samples of sounds speaking numbers form 1 to 5 recorded by 10 people.\n\u003cbr\u003e\n\u003cbr\u003eAccuracy on large (\u003e10k) dataset: 94%. \n\u003cbr\u003eAccuracy on given small  dataset: 93% \n\u003cbr\u003e\nTask was more or less chalenging because of small dataset.  \n\u003cbr\u003e\nAugmentation techniques:\n*   increase/decrease pitch\n*   increase/decrease speed\n*   stretching\n*   frequency and time masking\n*   white noice injection\n*   time shifting\n*   overlay 2 samples (quiet and louder)\n*   pre/post noise padding  \n\u003cbr\u003e\nSplitting data is done by speakers 5-5.\n\u003cbr\u003e\n\u003cbr\u003e\nTraining graph :\n\u003cbr\u003e\n\n![ ]( https://github.com/zvikiNozadze/MASR/blob/master/imgs/acc_graph.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzvikinoza%2Fmasr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzvikinoza%2Fmasr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzvikinoza%2Fmasr/lists"}