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.

We are using Levenshtein distance, which counts how many additions deletions and modifications are required to make one sequence into another.

https://en.wikipedia.org/wiki/Levenshtein_distance

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

See sample submission for details.