def prepare_training_data(sent_pairs):
voc = Vocabulary()
sent_pairs_normalized = []
for sent_p in sent_pairs:
# normalize incorrect and correct sentence in pair, and append them to normalized sentence pairs
incorrect_sent_normalized = normalize_string(sent_p[0])
correct_sent_normalized = normalize_string(sent_p[1])
normalized_sents_pair = (
incorrect_sent_normalized, correct_sent_normalized)
sent_pairs_normalized.append(normalized_sents_pair)
# add normalized sentence pair to vocabulary
voc.add_sentence_pair(normalized_sents_pair)
return voc, sent_pairs_normalized
