You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

42 lines
1.3 KiB

import os
import sys
import defaultfiles as default
from forced_alignment import pyhtk, convert_phone_set, scripts
reus_dir = r'c:\Users\Aki\source\repos\acoustic_model\reus-test'
wav_dir = reus_dir
wav_files = ['reus1008-reus.wav',
word = 'reus'
pronunciation_ipa = ['rø:s', 'mɑn', 'mɑntsjə']
for wav_file in wav_files:
file_lab = os.path.join(reus_dir, wav_file.replace('.wav', '.lab'))
file_dic = os.path.join(reus_dir, wav_file.replace('.wav', '.dic'))
file_txt = os.path.join(reus_dir, wav_file.replace('.wav', '.txt'))
# output htk dict file
with open(file_dic, 'w', encoding="utf-8") as f:
for ipa in pronunciation_ipa:
cgn = convert_phone_set.ipa2cgn([ipa.replace(':', 'ː')])
barbara = convert_phone_set.cgn2barbara(cgn)
f.write(word.upper() + '\t' + barbara + '\n')
# output htk label file.
pyhtk._create_label_file(word, file_lab)
'HVite','-T', '1',
'-C', default.config_hvite,
'-H', default.acoustic_model,
'-i', file_txt,
#'-S', script_file,
file_dic, default.phonelist_txt, os.path.join(wav_dir, wav_file)