HW3P2
This is the Kaggle competition for hw3p2. The WSJ dataset will be used for this contest. We are going to be using unaligned labels in this contest. That means you are given the list of phonemes for each utterance, but not which frames correspond to which phonemes. Inference of the alignment will require using CTC loss.
Read about Levenshtein Distance [here](https://en.wikipedia.org/wiki/Levenshtein_distance)
What does the data look like?
Input data is an array of utterances, each of which is shaped (frames, frequencies). Labels are simply the list of phonemes in the utterance [0-45]. There are 46 phoneme labels. The phoneme array will be as long as however many phonemes are in the utterance. We provide a lookup mapping each phoneme to a single character for the purposes of this competition. Example below:

The first sentence in the development set is the following:

THE FEMALE PRODUCES A LITTER OF TWO TO FOUR YOUNG IN NOVEMBER AND DECEMBER

The first item in the dev datafile is an array of ints. If you were to print those integers using our map of phonemes to characters, you would print the following:

.DhfImElpRhdUsizhlitrhvtUtifoR?hGinnOvembrAnddisembr_.

If you sound it out, you can convince yourself that these are the phonemes for the sentence above.
The Task
Predict the phonemes contained in utterances in the test set. You are not given aligned phonemes in the training data, and you are not asked to produce alignment for the test data.