{"id":17820700,"url":"https://github.com/orbxball/timit-preprocessor","last_synced_at":"2025-03-18T08:31:22.125Z","repository":{"id":89118229,"uuid":"112911794","full_name":"orbxball/timit-preprocessor","owner":"orbxball","description":"Extract mfcc vectors and phones from TIMIT dataset","archived":false,"fork":false,"pushed_at":"2023-03-23T04:28:54.000Z","size":7,"stargazers_count":15,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-02-28T09:11:40.765Z","etag":null,"topics":["data-preprocessing","deep-learning","mfcc","phone","speech-recognition","timit","timit-dataset"],"latest_commit_sha":null,"homepage":null,"language":"Shell","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/orbxball.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":"2017-12-03T08:24:31.000Z","updated_at":"2023-04-16T15:14:25.000Z","dependencies_parsed_at":"2023-06-14T00:45:30.278Z","dependency_job_id":null,"html_url":"https://github.com/orbxball/timit-preprocessor","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/orbxball%2Ftimit-preprocessor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/orbxball%2Ftimit-preprocessor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/orbxball%2Ftimit-preprocessor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/orbxball%2Ftimit-preprocessor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/orbxball","download_url":"https://codeload.github.com/orbxball/timit-preprocessor/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243922108,"owners_count":20369350,"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-preprocessing","deep-learning","mfcc","phone","speech-recognition","timit","timit-dataset"],"created_at":"2024-10-27T17:08:08.094Z","updated_at":"2025-03-18T08:31:22.120Z","avatar_url":"https://github.com/orbxball.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TIMIT Preprocessor\n\n**timit-preprocessor** extract mfcc vectors and phones from TIMIT dataset for advanced use on speech recognition.\n\n## Overview\nThe TIMIT corpus of read speech is designed to provide speech data for acoustic-phonetic studies and for the development and evaluation of automatic speech recognition systems. More information on [website](https://catalog.ldc.upenn.edu/ldc93s1) or [Wiki](https://en.wikipedia.org/wiki/TIMIT)\n\n## Installation\n\nNote that to install [Kaldi](https://github.com/kaldi-asr/kaldi) first by following the instructions in [`INSTALL`](https://github.com/kaldi-asr/kaldi/blob/master/INSTALL).\n\n\u003e (1)  \n\u003e go to tools/ and follow INSTALL instructions there.  \n\u003e\n\u003e (2) \n\u003e go to src/ and follow INSTALL instructions there.  \n\nAfter running the scripts instructed by `INSTALL` in `tools/`, there will be reminder as followed. Go and run it.\n\n\u003e Kaldi Warning: IRSTLM is not installed by default anymore. If you need IRSTLM, use the script `extras/install_irstlm.sh`\n\nAfter ensuring kaldi installation, we can start by running\n\n```\ngit clone https://github.com/orbxball/timit-preprocessor.git\n```\n\n## Preprocessing\n\n### Steps\n\n1. Run `./convert_wav.sh` only in the **first time** after cloning this repo.\n\n2. `python3 parsing.py -h` to see instructions parsing timit dataset for phone labels and raw intermediate files in folder `data/material/`.\n\n3. `./extract_mfcc.sh` to extract mfcc vectors into .scp and .ark files.\n\nFinally, there's a folder called `data/` which contains all the outcomes in the belowing directory structure:\n\n```\ndata/\n|-- material\n|   |-- test.lbl\n|   `-- train.lbl\n`-- processed\n    |-- test.39.cmvn.ark\n    |-- test.39.cmvn.scp\n    |-- test.extract.log\n    |-- train.39.cmvn.ark\n    |-- train.39.cmvn.scp\n    `-- train.extract.log\n```\n\nIf you want to do further operations, there's a good repo called [kaldi-io-for-python](https://github.com/vesis84/kaldi-io-for-python).\n\n## Contact\nFeel free to [contact me](mailto:junyouliu9@gmail.com) if there's any problems.\n\n### License\n\nBSD 3-Clause License (2017), Jun-You Liu\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Forbxball%2Ftimit-preprocessor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Forbxball%2Ftimit-preprocessor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Forbxball%2Ftimit-preprocessor/lists"}