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.

138 lines
3.8 KiB

import numpy as np
import defaultfiles as default
def load_phonset():
translation_key_ipa2novo70 = dict()
translation_key_novo702ipa = 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.novo70_phoneset, "rt", encoding="utf-8") as fin:
lines = fin.read()
lines = lines.split('\n')
for line in lines:
words = line.split('\t')
if len(words) > 1:
novo70 = words[0]
ipa = words[1]
phoneset_ipa.append(ipa)
phoneset_novo70.append(novo70)
translation_key_ipa2novo70[ipa] = novo70
translation_key_novo702ipa[novo70] = ipa
phoneset_ipa = np.unique(phoneset_ipa)
phoneset_novo70 = np.unique(phoneset_novo70)
return phoneset_ipa, phoneset_novo70, translation_key_ipa2novo70, translation_key_novo702ipa
def multi_character_tokenize(line, multi_character_tokens):
"""
Tries to match one of the tokens in multi_character_tokens at each position of line,
starting at position 0,
if so tokenizes and eats that token. Otherwise tokenizes a single character.
Copied from forced_alignment.convert_phone_set.py
"""
while line != '':
for token in multi_character_tokens:
if line.startswith(token) and len(token) > 0:
yield token
line = line[len(token):]
break
else:
yield line[:1]
line = line[1:]
def split_ipa(line):
"""
Split a line by IPA phones.
If nasalized sound (such as ɛ̃ː) is included, it will give error.
:param string line: one line written in IPA.
:return string lineSeperated: the line splitted in IPA phone.
"""
multi_character_phones = [
# IPAs in CGN.
u'ʌu', u'ɛi', u'œy', u'', u'', u'', u'', u'øː', u'ɛː', u'œː', u'ɔː', u'ɛ̃ː', u'ɑ̃ː', u'ɔ̃ː', u'œ̃', u'ɪː'
]
return [phone for phone in multi_character_tokenize(line.strip(), multi_character_phones)]
def split_novo70(line):
"""
Split a line by novo70 phones.
:param string line: one line written in novo70.
:return string lineSeperated: the line splitted by novo70 phones.
"""
_, phoneset_novo70, _, _ = load_phonset()
multi_character_phones = [p for p in phoneset_novo70 if len(p) > 1]
multi_character_phones = sorted(multi_character_phones, key=len, reverse=True)
return ['sp' if phone == ' ' else phone
for phone in multi_character_tokenize(line.strip(), multi_character_phones)]
def novo702ipa(tokens):
pronunciation = []
_, _, _, translation_key = load_phonset()
for phone in split_novo70(tokens):
pronunciation.append(translation_key.get(phone, phone))
return ' '.join(pronunciation)
# numbering of novo70 should be checked.
def ipa2novo70(tokens):
pronunciation = []
_, _, translation_key, _ = load_phonset()
for phone in split_ipa(tokens):
pronunciation.append(translation_key.get(phone, phone))
return ' '.join(pronunciation)
def make_grammar(word, pronunciation_ipa):
"""
Args:
words
pronunciation_ipa: list of pronunciation variants.
"""
#word = 'pauw'
#pronunciation_ipa = ['pau', 'pɑu']
grammer_data_elements0_pronunciation = []
for id, ipa in enumerate(pronunciation_ipa):
novo70 = novoapi_functions.ipa2novo70(ipa)
grammer_data_elements0_pronunciation.append({
"phones": novo70.split(),
"id": id
})
grammar_data = {
"kind": 'sequence',
"elements": [{
"kind": "word",
"pronunciation": grammer_data_elements0_pronunciation,
"label": word
}]
}
grammar = {
"type": "confusion_network",
"version": "1.0",
"data": grammar_data,
"return_objects": ["grammar"],
"phoneset": "novo70"
}
return grammar