You will be evaluated using Kaggle's character-level string edit distance. Since we mapped each phoneme to a single character, that means you are being evaluated on phoneme edit distance.
<\p>
We are using Levenshtein distance, which counts how many additions deletions and modifications are required to make one sequence into another.
<\p>
[https://en.wikipedia.org/wiki/Levenshtein_distance](https://en.wikipedia.org/wiki/Levenshtein_distance)
<\p>
Your submission should be a CSV file. The headers should be "Id", and "Predicted". - Id refers to the 0-based index of utterance in the test set - Predicted is the phoneme string
<\p>
See sample submission for details.