def getPhonScores(puns):
b = BlickLoader()
scoredPuns = {}
for pun in puns:
words = pun.split('#')
del words[len(words) - 1]
goodWords = []
for w in words:
if "D I C T" not in w:
goodWords.append(w)
scoredPuns[pun] = sum(b.assessWord(w.strip()) for w in goodWords)
return scoredPuns
def train_wakeword_model(audio_train_loader,
vocab_list,
label_model,
beam_size=3,
num_hypotheses=5,
query_by_string=False):
wakeword_model = {}
if query_by_string:
# load ww model produced by MFA from config
keywords = config["wakeword_model"]
# load blick
b = BlickLoader()
for i, _, y_hat in enumerate(keywords.items()):
w = b.assessWord(y_hat)
# for each keyword, append the tuple(hypotheses + weights) to the list
# only one hypothesis if using MFA
wakeword_model[i] = (y_hat, w)
else:
# train ww model from scratch
for i in audio_train_loader:
posteriors_i = label_model(i)
# decode using CTC, vocab_list is A (labels)
decoder = CTCBeamDecoder(self.vocab_list,
beam_width=self.beam_size,
blank_id=self.vocab_list.index('_'))
beam, beam_scores, _, _ = decoder.decode(posteriors_i)
for j in range(num_hypotheses):
y_hat = beam[j] # hypothesis
log_prob_post = beam_scores[j]
w = log_prob_post**-1
# for each keyword, append the tuple(hypotheses + weights) to the list
wakeword_model[i].append((y_hat, w))
return wakeword_model
if syl.nucleus in SHORT_VOWELS:
return False
if is_first and syl.onset and syl.onset[0] == "ZH":
return False
# if is_last and stress_lvl == 1 and len(syl.coda) == 0:
# return False
if syl.onset and syl.coda and syl.onset[0] == "S" and not syl.onset[
-1] == "T" and syl.nucleus in SHORT_VOWELS:
if syl.coda[0] == syl.onset[-1]:
return False
if stress_lvl != 1 and syl.nucleus not in {
"AH", "ER", "IH", "IY", "OW", "UW"
}:
return False
return True
blick_rater = BlickLoader()
words = []
for i in range(100):
word = getWord()
score, rules = blick_rater.assessWord(word.replace(" ", " "),
includeConstraints=True)
score = exp(-score)
words.append([word, score, rules])
for word, score, rules in sorted(words, key=itemgetter(1)):
if score > 0.00001:
print(word, score, rules)
print()
from blick import BlickLoader
parser = argparse.ArgumentParser(
description='Add phonotactic probability to a file of phone strings.')
parser.add_argument('filename',
type=open,
help='name of file of phone strings')
parser.add_argument('-d',
'--debug',
action='store_true',
default=False,
help='whether or not debug mode should be activated')
parser.add_argument('-c',
'--constraints',
action='store_true',
default=False,
help='whether or not debug mode should be activated')
parser.add_argument('-g',
'--grammar',
type=str,
choices=set(['HayesWhite', 'NoStress', 'default']),
default='default',
help='type of grammar to be used')
args = parser.parse_args()
argdict = vars(args)
#print argdict
b = BlickLoader(debug=argdict['debug'], grammarType=argdict['grammar'])
b.assessFile(argdict['filename'].name,
includeConstraints=argdict['constraints'])
