# 104-1 MLDS_HW2 — Data

来源：https://www.kaggle.com/competitions/104-1-mlds-hw2/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<p>The data is exactly the same as in homework 1 except we add one file 'phones/48_idx_chr.map' which provides the mapping from 48 phoneme to the corresponding index and English character. You may download the file '48_idx_chr.map' directly if you already have the training data in homework 1.</p>
<p>Also, we provide you the posterior gram of both testing and training set after a trained DNN. If you didn't get good result in homework 1, then you may try to train you RNN with this given posterior gram.</p>