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.

56 lines
1.5 KiB

import os
import sys
import csv
#import subprocess
#from collections import Counter
#import re
import numpy as np
import pandas as pd
#import matplotlib.pyplot as plt
#from sklearn.metrics import confusion_matrix
import acoustic_model_functions as am_func
import convert_xsampa2ipa
import defaultfiles as default
from forced_alignment import pyhtk
import novoapi
## ======================= convert phones ======================
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', default.ipa_xsampa_converter_dir)
stimmen_transcription_ = pd.ExcelFile(default.stimmen_transcription_xlsx)
## novo phoneset
translation_key = dict()
#phonelist_novo70_ = pd.ExcelFile(default.phonelist_novo70_xlsx)
#df = pd.read_excel(phonelist_novo70_, 'list')
## *_simple includes columns which has only one phone in.
#for ipa, novo70 in zip(df['IPA_simple'], df['novo70_simple']):
# if not pd.isnull(ipa):
# print('{0}:{1}'.format(ipa, novo70))
# translation_key[ipa] = novo70
#phonelist_novo70 = np.unique(list(df['novo70_simple']))
phoneset_ipa = []
phoneset_novo70 = []
with open(default.cmu69_phoneset, "rt", encoding="utf-8") as fin:
lines =
lines = lines.split('\n')
for line in lines:
words = line.split('\t')
if len(words) > 1:
novo70 = words[0]
ipa = words[1]
translation_key[ipa] = novo70
phoneset_ipa = np.unique(phoneset_ipa)
phoneset_novo70 = np.unique(phoneset_novo70)