HW3P2
This is the Kaggle competition for hw3p2. The 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 [0-40]. There are 41 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.
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.