{"id":18563429,"url":"https://github.com/reddiedev/197z-kws","last_synced_at":"2025-05-15T18:13:25.457Z","repository":{"id":171159687,"uuid":"647529776","full_name":"reddiedev/197z-kws","owner":"reddiedev","description":"zero-shot keyword spotting with KWS test dataset using ImageBind","archived":false,"fork":false,"pushed_at":"2023-06-12T15:21:55.000Z","size":2855,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-15T18:13:25.189Z","etag":null,"topics":["imagebind","kws","pytorch-audio","speech-commands","zero-shot"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/reddiedev.png","metadata":{"files":{"readme":"README.md","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":"2023-05-31T01:35:24.000Z","updated_at":"2023-06-12T15:08:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"5f575593-9e6e-4520-bc03-d9c96cfc79c0","html_url":"https://github.com/reddiedev/197z-kws","commit_stats":null,"previous_names":["reddiedev/197z-kws"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reddiedev%2F197z-kws","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reddiedev%2F197z-kws/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reddiedev%2F197z-kws/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reddiedev%2F197z-kws/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/reddiedev","download_url":"https://codeload.github.com/reddiedev/197z-kws/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254394726,"owners_count":22063984,"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":["imagebind","kws","pytorch-audio","speech-commands","zero-shot"],"created_at":"2024-11-06T22:12:38.987Z","updated_at":"2025-05-15T18:13:25.436Z","avatar_url":"https://github.com/reddiedev.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EEE 197z Project 2 - Zero-Shot KWS using ImageBind\nan algorithm using ImageBind that will classify KWS test dataset (Google Speech Commands v2 35) in zero-shot manner. \n\n*Author: Sean Red Mendoza | 2020-01751 | scmendoza5@up.edu.ph*\n\n## Tools/ References\n- [ImageBind](https://github.com/facebookresearch/ImageBind)\n- [Gradio](https://gradio.app/)\n- [roatienza/Deep-Learning-Experiments](https://github.com/roatienza/Deep-Learning-Experiments)\n- [Google Cloud G2 GPU VM (2x Nvidia L4)](https://cloud.google.com/blog/products/compute/introducing-g2-vms-with-nvidia-l4-gpus)\n\n## Goals\n- [x] randomly pick an audio from the test split and classify it (audio player in UI)\n- [x] user should be able to record his/her own voice for testing (audio recorder in UI, powered by Gradio)\n- [x] show summary statistics during evaluation of n sampels (# of data points, accuracy).\n- [x] comparison table of SOTA model scores\n\n# Usage\n\n1. Duplicate this repository on a working directory\n```bash\ngit clone https://github.com/reddiedev/197z-kws\ncd 197z-kws\n```\n\n2. Prepare environment for running the notebook\n\n```bash\nconda create --name kws\nconda activate kws\n\nsudo apt install ffmpeg\n\npip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118\npip jupyter jupyterlab ipywidgets==7.6.5 install numpy ipython gradio ipywebrtc notebook\n\njupyter labextension install jupyter-webrtc \n\n```\n\n3. Run the `demo.ipynb` jupyter notebook\n\n4. View SOTA models comparison in `comparison.md`\n\n# Acknowledgements\n[Professor, Rowel Atienza](https://github.com/roatienza)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freddiedev%2F197z-kws","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freddiedev%2F197z-kws","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freddiedev%2F197z-kws/lists"}