{"id":16634248,"url":"https://github.com/qanastek/ner-mmtd","last_synced_at":"2026-04-22T11:06:01.716Z","repository":{"id":130429188,"uuid":"365219957","full_name":"qanastek/NER-MMTD","owner":"qanastek","description":"Named-entity recognition corpora for multilingual voice recognition in the music industry based on the Million Musical Tweets dataset","archived":false,"fork":false,"pushed_at":"2021-05-08T01:52:04.000Z","size":1757,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-12-26T22:45:55.567Z","etag":null,"topics":["corpora","dataset","english","french","million-musical-tweets","mmtd","music","named-entity-recognition","ner","neural-network","recognition","voice"],"latest_commit_sha":null,"homepage":"","language":"Python","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/qanastek.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":"2021-05-07T12:03:21.000Z","updated_at":"2021-05-08T01:52:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"b02472f7-7701-4127-b604-d9fb57583276","html_url":"https://github.com/qanastek/NER-MMTD","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/qanastek/NER-MMTD","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qanastek%2FNER-MMTD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qanastek%2FNER-MMTD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qanastek%2FNER-MMTD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qanastek%2FNER-MMTD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/qanastek","download_url":"https://codeload.github.com/qanastek/NER-MMTD/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qanastek%2FNER-MMTD/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32132975,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-22T08:34:57.708Z","status":"ssl_error","status_checked_at":"2026-04-22T08:34:55.583Z","response_time":58,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["corpora","dataset","english","french","million-musical-tweets","mmtd","music","named-entity-recognition","ner","neural-network","recognition","voice"],"created_at":"2024-10-12T05:32:46.869Z","updated_at":"2026-04-22T11:06:01.695Z","avatar_url":"https://github.com/qanastek.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NER-MMTD\nNamed-entity recognition corpora for multilingual recognition in the music industry based on the Million Musical Tweets dataset\n\n## Steps\n\n- Clone the project\n- Download the MMTD corpora [here](http://www.cp.jku.at/datasets/MMTD/)\n- Extract the files `artists.txt` and `track.txt` into `data/raw`\n- If you want to generate the corpora again run `python getInfos.py`\n\n## State-of-the-art\n\nUsing [Flair](https://github.com/flairNLP/flair) and CRF on 100 epochs (1.5 hours on a E5-2690 v1):\n\n|                  | precision | recall | f1-core |\n|------------------|-----------|--------|---------|\n| ARTIST           | 98.10%    | 100%   | 99.06%  |\n| PAUSE            | 100%      | 100%   | 100%    |\n| START            | 100%      | 100%   | 100%    |\n| STOP             | 100%      | 100%   | 100%    |\n| TRACK            | 99.42%    | 99.42% | 99.42%  |\n| F1-score (macro) |           |        | 99.70%  |\n\n## Sources\n\n- http://www.cp.jku.at/datasets/MMTD/\n- http://www.diva-portal.se/smash/get/diva2:1010104/FULLTEXT01.pdf\n\n## Citation\n\nIf you want to use this corpora in your research, please cite the following ressources:\n\n```BibTeX\n@inproceedings{inproceedings,\n  author = {Hauger, David and Kosir, Andrej and Tkalčič, Marko and Schedl, Markus},\n  year = {2013},\n  month = {11},\n  pages = {},\n  title = {THE MILLION MUSICAL TWEETS DATASET: WHAT CAN WE LEARN FROM MICROBLOGS}\n}\n\n@misc{labrak_yanis_ner_mmtd,\n  author       = {Labrak Yanis},\n  title        = {Named-entity recognition corpora for multilingual voice recognition in the music industry},\n  month        = may,\n  year         = 2021,\n  version      = {1.0},\n  publisher    = {GitHub},\n  url          = {https://github.com/qanastek/NER-MMTD}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqanastek%2Fner-mmtd","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqanastek%2Fner-mmtd","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqanastek%2Fner-mmtd/lists"}