# Homework 3 Part 2 11-785 slack — Data

来源：https://www.kaggle.com/competitions/11785-s19-hw3p2-slack/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>Data Files</h2>
<p>Data files are available for download from this page.</p>
<h2>File Descriptions </h2>
<ul>
<li><strong>transformed_test_data.npy</strong> - test features</li>
<li><strong>wsj0_train.npy</strong> - train features</li>
<li><strong>wsj0_dev.npy</strong> - development/validation features</li>
<li><strong> wsj0_train_merged_labels.npy </strong> - training labels</li>
<li><strong> wsj0_dev_merged_labels.npy </strong> - development/validation labels</li>
<li><strong> sample_submission.csv </strong> -  sample submission in correct format. Submission is a single silence phoneme (".") for each utterance. </li>
<li><strong> phoneme_list.py </strong> -  List of phoneme full names, and list of phoneme single-character encodings. </li>
<h2> Feature Files </h2>
<p> Same data layout as previously. </p>
<h2> Label Files </h2>
<p> Array length is the number of utterances. Each item in the array is an array that is the length of the number of phonemes in that utterance. The labels are [0-45], 46 phonemes.</p>