Last active
April 11, 2023 15:42
-
-
Save Witty-Kitty/96894aadfbe971997d27cdbb1d14196e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python3 | |
| import argparse | |
| import epitran | |
| def get_phoneme_string(epi,word): | |
| phoneme_tuples = epi.word_to_tuples(word) | |
| num = 0 | |
| phoneme_list = [] | |
| while num < len(phoneme_tuples): | |
| phoneme_list.append(phoneme_tuples[num][3]) | |
| num += 1 | |
| return ' '.join(phoneme_list) | |
| def main(): | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument( | |
| "-f", | |
| "--file", | |
| "--frequencies-file", | |
| required=True, | |
| help="path to .txt file containing words and their frequencies", | |
| type=str | |
| ) | |
| epi = epitran.Epitran('swa-Latn') | |
| args = parser.parse_args() | |
| lexicon_info_tuples = [] | |
| with open(args.file, 'r') as f: | |
| for line in f: | |
| tuple_items = line.strip().split() # split each line into tuple items | |
| phonemes = get_phoneme_string(epi,tuple_items[0]) | |
| my_tuple = (tuple_items[0], phonemes, tuple_items[1]) # create a tuple from the items | |
| lexicon_info_tuples.append(my_tuple) | |
| with open('lexicon-default.xml', 'w') as f: | |
| f.write('<lexicon> \n') | |
| for lexicon_tuple in lexicon_info_tuples: | |
| f.write('<lex pron="' + lexicon_tuple[1] + '" default="true" freq="' + lexicon_tuple[2] + '">' + lexicon_tuple[0] + '</lex> \n') | |
| f.write('</lexicon>') | |
| if __name__ == "__main__": | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment