{
 "id": "nguyendv02/ViMD_Dataset",
 "owner": "nguyendv02",
 "name": "ViMD_Dataset",
 "downloads": 4309,
 "likes": 24,
 "last_modified": "2026-01-28T10:19:27.000Z",
 "stated_licence": "cc-by-nc-nd-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{dinh-etal-2024-multi,\n    title = \"Multi-Dialect {V}ietnamese: Task, Dataset, Baseline Models and Challenges\",\n    author = \"Dinh, Nguyen  and\n      Dang, Thanh  and\n      Thanh Nguyen, Luan  and\n      Nguyen, Kiet\",\n    editor = \"Al-Onaizan, Yaser  and\n      Bansal, Mohit  and\n      Chen, Yun-Nung\",\n    booktitle = \"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2024\",\n    address = \"Miami, Florida, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.emnlp-main.426\",\n    pages = \"7476--7498\",\n    abstract = \"Vietnamese, a low-resource language, is typically categorized into three primary dialect groups that belong to Northern, Central, and Southern Vietnam. However, each province within these regions exhibits its own distinct pronunciation variations. Despite the existence of various speech recognition datasets, none of them has provided a fine-grained classification of the 63 dialects specific to individual provinces of Vietnam. To address this gap, we introduce Vietnamese Multi-Dialect (ViMD) dataset, a novel comprehensive dataset capturing the rich diversity of 63 provincial dialects spoken across Vietnam. Our dataset comprises 102.56 hours of audio, consisting of approximately 19,000 utterances, and the associated transcripts contain over 1.2 million words. To provide benchmarks and simultaneously demonstrate the challenges of our ",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-nd-4.0) is classified as having use restrictions.",
 "revision": "3a5b30157034e7eadd5c75fae1a820c6f9383398",
 "stated_evidence": "https://huggingface.co/datasets/nguyendv02/ViMD_Dataset/blob/3a5b30157034e7eadd5c75fae1a820c6f9383398/README.md",
 "file_evidence": "https://huggingface.co/datasets/nguyendv02/ViMD_Dataset/tree/3a5b30157034e7eadd5c75fae1a820c6f9383398",
 "card_nc": false
}