{"id":20535167,"url":"https://github.com/daniel05155/unlearning-information-in-speech-recognition-model","last_synced_at":"2026-04-11T22:34:43.578Z","repository":{"id":248799802,"uuid":"829812311","full_name":"daniel05155/Unlearning-Information-in-Speech-Recognition-Model","owner":"daniel05155","description":"This repository is an implementation of machine unlearning in deep learning model.","archived":false,"fork":false,"pushed_at":"2024-07-17T13:41:24.000Z","size":21,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-16T13:49:24.765Z","etag":null,"topics":["data-deletion","deep-learning","machine-unlearning","privacy","privacy-protection","speech-recognition"],"latest_commit_sha":null,"homepage":"","language":"Python","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/daniel05155.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":"2024-07-17T03:40:38.000Z","updated_at":"2024-07-17T13:41:27.000Z","dependencies_parsed_at":null,"dependency_job_id":"1e32fd0b-8f1e-49f3-bd28-1be3c7dc41da","html_url":"https://github.com/daniel05155/Unlearning-Information-in-Speech-Recognition-Model","commit_stats":null,"previous_names":["daniel05155/unlearning-information-in-speech-recognition-model"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daniel05155%2FUnlearning-Information-in-Speech-Recognition-Model","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daniel05155%2FUnlearning-Information-in-Speech-Recognition-Model/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daniel05155%2FUnlearning-Information-in-Speech-Recognition-Model/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daniel05155%2FUnlearning-Information-in-Speech-Recognition-Model/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/daniel05155","download_url":"https://codeload.github.com/daniel05155/Unlearning-Information-in-Speech-Recognition-Model/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242139755,"owners_count":20078174,"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":["data-deletion","deep-learning","machine-unlearning","privacy","privacy-protection","speech-recognition"],"created_at":"2024-11-16T00:29:33.980Z","updated_at":"2026-04-11T22:34:38.556Z","avatar_url":"https://github.com/daniel05155.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Unlearning-Information-in-Speech-Recognition-Model\n\nNowadays, machine learning systems store a vast amount of training data. \nHowever, due to model inversion or membership inference attacks, certain private information from the training dataset may be exposed.\nAlthough deleting data from back-end databases ought to be simple, doing so is insufficient when it comes to artificial intelligence (AI) because machine learning models frequently retain historical data. \nTo address the above problem, we require a novel method known as machine unlearning, which enables deep learning models to forget about specific data following the training stage. \nThrough the machine unlearing(MU) techniques, we are able to eliminate specific memories from the speech recognition model.\n\n## Requirements\n- Python 3.10\n- PyTorch\n\n### Install Environment\n```\nconda env create -f environment.yaml\n```\n\n## Usage\n\n### Dataset\nWe use the [Google Speech Commands Dataset (v0.02)](https://arxiv.org/abs/1804.03209) as the training dataset.\n\n### Commands\n* Training\n```\npython main.py --epochs 50 --lr 0.01 --batch_size 256 \n```\n\n* Retrain\n```\npython main.py --retrain  --epochs 50\n```\n\n* Transfer learning\n```\npython unlearn_TS.py\n```\n\n* Uncertainty Enhancing\n```\npython advloss.py\n```\n\n* Inference\n```\npython inference.py\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdaniel05155%2Funlearning-information-in-speech-recognition-model","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdaniel05155%2Funlearning-information-in-speech-recognition-model","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdaniel05155%2Funlearning-information-in-speech-recognition-model/lists"}