Dataset Open Access

Nganasan and Kamas Speech Recognition Models

Partanen, Niko; Hämäläinen, Mika; Klooster, Tiina


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/emur_kamas_batches.R"
      }, 
      "checksum": "md5:1098c8cd6ea53dbc59e75b8c10091ab4", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "emur_kamas_batches.R", 
      "type": "r", 
      "size": 12753
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/emur_kamas_restructure.R"
      }, 
      "checksum": "md5:5998b3e977d68227666a910a5e453c81", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "emur_kamas_restructure.R", 
      "type": "r", 
      "size": 5384
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/experiment_01_data.zip"
      }, 
      "checksum": "md5:c9d9c48d44513461c629eee85516aa1a", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "experiment_01_data.zip", 
      "type": "zip", 
      "size": 741298485
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/experiment_02_data.zip"
      }, 
      "checksum": "md5:fd2edafd69f70bec128e6aeca1602ed4", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "experiment_02_data.zip", 
      "type": "zip", 
      "size": 335134339
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/experiment_03_data.zip"
      }, 
      "checksum": "md5:3b23815a42f18f97a3282032ce8a58c2", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "experiment_03_data.zip", 
      "type": "zip", 
      "size": 391067762
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/experiment_07_10_data.zip"
      }, 
      "checksum": "md5:096dd12ab7cfc32605462a859929440f", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "experiment_07_10_data.zip", 
      "type": "zip", 
      "size": 2582530402
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/models_and_scripts.zip"
      }, 
      "checksum": "md5:1cb081c4b5866523f9b10e68e3bbf6b4", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "models_and_scripts.zip", 
      "type": "zip", 
      "size": 707589843
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/preprocess_kamas.py"
      }, 
      "checksum": "md5:161f36b4fd60edc96cc284499d60d541", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "preprocess_kamas.py", 
      "type": "py", 
      "size": 4404
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/preprocess_nganasan.py"
      }, 
      "checksum": "md5:f7e495f0939bbc59666e72beea98fa9c", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "preprocess_nganasan.py", 
      "type": "py", 
      "size": 6412
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/README.md"
      }, 
      "checksum": "md5:ad377a95cd3ba5979713c4d8d1b7145e", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "README.md", 
      "type": "md", 
      "size": 3510
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/sampa_inventory.txt"
      }, 
      "checksum": "md5:2c7b8131d54e89ad2d4f12c56c6577be", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "sampa_inventory.txt", 
      "type": "txt", 
      "size": 50924
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28/xas-sampa.txt"
      }, 
      "checksum": "md5:acd31c7719220e51118bab3d359d8db3", 
      "bucket": "e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
      "key": "xas-sampa.txt", 
      "type": "txt", 
      "size": 318
    }
  ], 
  "owners": [
    40509
  ], 
  "doi": "10.5281/zenodo.4029494", 
  "stats": {
    "version_unique_downloads": 6.0, 
    "unique_views": 27.0, 
    "views": 33.0, 
    "version_views": 33.0, 
    "unique_downloads": 6.0, 
    "version_unique_views": 27.0, 
    "volume": 4757825228.0, 
    "version_downloads": 19.0, 
    "downloads": 19.0, 
    "version_volume": 4757825228.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.4029494", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.4029493", 
    "bucket": "https://zenodo.org/api/files/e87ce363-b7aa-4387-87fc-2042e4f4ad28", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.4029493.svg", 
    "html": "https://zenodo.org/record/4029494", 
    "latest_html": "https://zenodo.org/record/4029494", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.4029494.svg", 
    "latest": "https://zenodo.org/api/records/4029494"
  }, 
  "conceptdoi": "10.5281/zenodo.4029493", 
  "created": "2020-09-25T11:16:18.292162+00:00", 
  "updated": "2020-09-26T12:26:53.192385+00:00", 
  "conceptrecid": "4029493", 
  "revision": 3, 
  "id": 4029494, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.4029494", 
    "description": "<p>These are the models trained in our paper</p>\n\n<p>Partanen, N., H&auml;m&auml;l&auml;inen, M. and Klooster, T. (2020)&nbsp;Speech Recognition for Endangered and Extinct Samoyedic languages. In&nbsp;<em>Proceedings of&nbsp;the 34th Pacific Asia Conference on Language, Information and Computation</em>.</p>\n\n<p>See the readme for more</p>\n\n<p><sub>Based on corpora from</sub></p>\n\n<p><sub>Gusev, Valentin; Klooster, Tiina; Wagner-Nagy, Be&aacute;ta. 2019. &quot;INEL Kamas Corpus.&quot; Version 1.0. Publication date 2019-12-15. http://hdl.handle.net/11022/0000-0007-DA6E-9. Archived in Hamburger Zentrum f&uuml;r Sprachkorpora. In: Wagner-Nagy, Be&aacute;ta; Arkhipov, Alexandre; Ferger, Anne; Jettka, Daniel; Lehmberg, Timm (eds.). The INEL corpora of indigenous Northern Eurasian languages.</sub></p>\n\n<p><sub>Maria Brykina, Valentin Gusev, Sandor Szever&eacute;nyi, and Be&aacute;ta Wagner-Nagy. 2018. Nganasan spoken language corpus (nslc). Archived in Hamburger Zentrumf&uuml;r Sprachkorpora. Version 0.2. Publication date, 12.</sub></p>", 
    "language": "nio", 
    "title": "Nganasan and Kamas Speech Recognition Models", 
    "license": {
      "id": "CC-BY-NC-SA-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "4029493"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "4029494"
          }
        }
      ]
    }, 
    "version": "1.0", 
    "publication_date": "2020-09-14", 
    "creators": [
      {
        "orcid": "0000-0001-8584-3880", 
        "affiliation": "University of Helsinki", 
        "name": "Partanen, Niko"
      }, 
      {
        "orcid": "0000-0001-9315-1278", 
        "affiliation": "University of Helsinki", 
        "name": "H\u00e4m\u00e4l\u00e4inen, Mika"
      }, 
      {
        "affiliation": "Luua Forestry School", 
        "name": "Klooster, Tiina"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.4029493", 
        "relation": "isVersionOf"
      }
    ]
  }
}
33
19
views
downloads
All versions This version
Views 3333
Downloads 1919
Data volume 4.8 GB4.8 GB
Unique views 2727
Unique downloads 66

Share

Cite as