{"id":20046601,"url":"https://github.com/ncsoft/phonmatchnet","last_synced_at":"2025-05-05T09:31:44.235Z","repository":{"id":214265316,"uuid":"644226719","full_name":"ncsoft/PhonMatchNet","owner":"ncsoft","description":"Official implementation of \"PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords\" (INTERSPEECH 2023)","archived":false,"fork":false,"pushed_at":"2024-06-03T00:57:33.000Z","size":4508,"stargazers_count":46,"open_issues_count":3,"forks_count":8,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-04-08T20:51:36.824Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ncsoft.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":"2023-05-23T04:54:41.000Z","updated_at":"2025-03-21T08:14:18.000Z","dependencies_parsed_at":"2023-12-27T02:30:10.970Z","dependency_job_id":"9bbbc776-ee07-4db3-a9a6-74a79eda8108","html_url":"https://github.com/ncsoft/PhonMatchNet","commit_stats":null,"previous_names":["ncsoft/phonmatchnet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ncsoft%2FPhonMatchNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ncsoft%2FPhonMatchNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ncsoft%2FPhonMatchNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ncsoft%2FPhonMatchNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ncsoft","download_url":"https://codeload.github.com/ncsoft/PhonMatchNet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252471522,"owners_count":21753202,"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":[],"created_at":"2024-11-13T11:24:58.711Z","updated_at":"2025-05-05T09:31:43.349Z","avatar_url":"https://github.com/ncsoft.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# :mag: PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords\n\nOfficial implementation of PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords.\n\nPyTorch version: https://github.com/ncsoft/PhonMatchNet/tree/pytorch\n\n## Requirements\n\n### Datasets\n\n* [LibriPhrase](https://github.com/gusrud1103/libriphrase)\n\n* [Google Speech Commands](https://arxiv.org/abs/1804.03209)\n\n* [Qualcomm Keyword Speech](https://developer.qualcomm.com/project/keyword-speech-dataset)\n\nDownload the dataset and prepare it according to each guide. \n\n## Getting started\n\n### Environment\n\n```bash\ncd ./docker\ndocker build --tag udkws .\n```\n\n### Training\n\n```bash\ndocker run -it --rm --gpus '\"device=0,1\"' \\\n    -v /path/to/this/repo:/home/ \\\n    -v /path/to/prepared/dataset:/home/DB \\\n    ukws \\\n    /bin/bash -c \\\n    \"python train.py \\\n        --epoch 100 \\\n        --lr 1e-3 \\\n        --loss_weight 1.0 1.0 \\\n        --audio_input both \\\n        --text_input g2p_embed \\\n        --stack_extractor \\\n        --comment 'user comments for each experiment'\"\n\n```\n\n### Monitoring\n\n```bash\ntensorboard --logdir ./log/ --bind_all\n```\n\n## CONTRIBUTING\n\nPlease post bug reports and new feature suggestions to the Issues and Pull requests tabs of this repo.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fncsoft%2Fphonmatchnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fncsoft%2Fphonmatchnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fncsoft%2Fphonmatchnet/lists"}