{
  "fetched_at": "2026-10-19T07:12:58Z",
  "source_url": "https://www.kaggle.com/competitions/11-785-summer-20-homework-4-part-2/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>train_new.npy</strong> - The training set contains training utterances each of variable duration and 40 frequency bands.</li>\n<li><strong>train_transcripts.npy</strong> - These are the transcripts corresponding to the utterances in train.npy. These are arranged in the same order as the utterances.</li>\n<li><strong>dev_new.npyy</strong> -The development set contains validation utterances each of variable duration and 40 fre- quency bands.</li>\n<li><strong>train_transcripts.npy</strong> - These are the transcripts corresponding to the utterances in dev.npy. These are arranged in the same order as the utterances.</li>\n<li><strong>test_new.npy</strong> -  The test set contains test utterances each of variable duration and 40 frequency bands. There are no labels given for the test set.</li>\n<li><strong>test_sample_submission.csv</strong> - A sample submission file with correct format.</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "See writeup for more details.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric is Levenshtein mean. This is basically the mean number of inserts, edits, or deletions required to transform your submission into the true transcript. For an example submission, see the data page.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}