def test_search_stresses(self):
words = pronouncing.search_stresses('^000100$')
self.assertEqual(words, [
'phytogeography', 'uninterruptible', 'uninterruptible',
'variability'
])
words = pronouncing.search_stresses('^[12]0[12]0[12]0[12]$')
self.assertEqual(
words, ['dideoxycytidine', 'homosexuality', 'hypersensitivity'])
def test_search_stresses(self):
words = pronouncing.search_stresses('^000100$')
self.assertEqual(
words,
['phytogeography', 'uninterruptible', 'uninterruptible',
'variability'])
words = pronouncing.search_stresses('^[12]0[12]0[12]0[12]$')
self.assertEqual(
words,
['dideoxycytidine', 'homosexuality', 'hypersensitivity'])
def stress_pattern():
phones_list = pronouncing.phones_for_word("snappiest")
meter = pronouncing.stresses(phones_list[0])
print meter # 102
# 1 : primary stress, 2: secondary stress , 0: unstressed
## search by stress pattern
stress_first = pronouncing.search_stresses('100100')
stress_either = pronouncing.search_stresses(
'^00[12]00[12]$') ## either 1 or 2 in the []
print stress_first
print stress_either
def get_choices(word_pool, pat):
choices = pronouncing.search_stresses(pat)
new_list = []
for word in word_pool:
if word in choices:
new_list.append(word)
return new_list
def stress_search(stress_pattern):
regex = '^' + stress_pattern.replace('1', '[12]') + '$'
pat_len = len(stress_pattern)
results = []
while(not results):
results = pronouncing.search_stresses(regex)
pat_len -= 1
regex = '^' + stress_pattern[:pat_len].replace('1','[12]') + '$'
return results, pat_len + 1
def evaluate(prime_str=['f**k'], predict_len=4, temperature=0.8):
hidden = decoder.init_hidden()
prime_input = char_tensor(prime_str)
predicted = prime_str
target_meter = "1010101010"
target_rhyme = ""
# Use priming string to "build up" hidden state
for p in range(len(prime_str) - 1):
_, hidden = decoder(prime_input[p], hidden)
inp = prime_input[-1]
while predicted.count("\n") < predict_len:
output, hidden = decoder(inp, hidden)
# Sample from the network as a multinomial distribution
output_dist = output.data.view(-1).div(temperature).exp()
# print(output_dist)
top_i = torch.multinomial(output_dist, 1)[0]
# print(top_i)
# Add predicted character to string and use as next input
predicted_char = vocab[top_i]
# print(predicted_char)
if predicted_char.strip() != "":
if pronouncing.stresses_for_word(predicted_char):
word_meter = adjusted_meter(pronouncing.stresses_for_word(predicted_char)[0])
if target_meter.startswith(word_meter):
predicted += [predicted_char]
inp = char_tensor([predicted_char])
target_meter = target_meter[len(word_meter):]
if target_meter == "":
final_word = predicted.pop()
if target_rhyme != "":
meter_candidates = pronouncing.search_stresses(pronouncing.stresses_for_word(final_word)[0])
rhyme_candidates = pronouncing.rhymes(target_rhyme)
candidates = list(set(meter_candidates) & set(rhyme_candidates) & set(vocab))
if candidates:
#candidates = [output_dist[char_tensor([candidate])] for candidate in candidates if candidate in vocab]
#print([char_tensor([candidate]) for candidate in candidates])
final_word = random.choice(candidates)
predicted += [final_word, "\n"]
print(final_word)
if target_rhyme == "":
target_rhyme = final_word
else:
target_rhyme = ""
target_meter = "1010101010"
elif target_meter == "0":
target_meter = "1"
return predicted
def generate_joo_joo_eyeball(syllable_count):
text = [0]
while(text[0] != syllable_count):
text = random.choice(joo_joo_eyeball)
text = text[1] # Discard count, we don't need it
result = []
for word in text.split():
pronunciations = pronouncing.phones_for_word(word)
pat = pronouncing.stresses(pronunciations[0])
replacement = random.choice(pronouncing.search_stresses("^"+pat+"$"))
result.append(replacement)
return ' '.join(result)
def steal_voices():
words_ending_with_sounds = pr.search("S IH0 [ZS]$")
words_with_stresses = pr.search_stresses("[12][12]0")
words_with_sounds_and_stresses = set(
words_ending_with_sounds).intersection(words_with_stresses)
# Find words with correct syllable count
three_syllable_words = []
for word in words_with_sounds_and_stresses:
word_phones = pr.phones_for_word(word)
syllable_count = pr.syllable_count(word_phones[0])
if syllable_count == 3:
three_syllable_words.append(word)
return three_syllable_words
def summon_seas():
# Find words with mattching stress patterns
caspian_phones = pr.phones_for_word("caspian")
caspian_stresses = pr.stresses(caspian_phones[0])
words_with_stress_pattern = pr.search_stresses(caspian_stresses)
# Find words with correct syllable count
three_syllable_words = []
for word in words_with_stress_pattern:
word_phones = pr.phones_for_word(word)
syllable_count = pr.syllable_count(word_phones[0])
if syllable_count == 3:
sea = string.capwords((word + " sea"))
three_syllable_words.append(sea)
return three_syllable_words
def find_words():
# Find words with mattching stress patterns
beluga_phones = pr.phones_for_word("beluga")
last_beluga_phone = pr.phones_for_word("beluga")[0].split(" ")[-1]
beluga_stresses = pr.stresses(beluga_phones[0])
words_with_stress_pattern = pr.search_stresses(beluga_stresses)
# Find words with matching end phone
words_ending_with_ah = pr.search(last_beluga_phone + "$")
# Find words with correct syllable count
words_with_stress_and_ending = list(
set(words_with_stress_pattern).intersection(words_ending_with_ah))
three_syllable_words = []
for word in words_with_stress_and_ending:
word_phones = pr.phones_for_word(word)
syllable_count = pr.syllable_count(word_phones[0])
if syllable_count == 3:
three_syllable_words.append(word)
return three_syllable_words
def evaluate_prob(prime_str=['f**k'], predict_len=4, temperature=0.8):
hidden = decoder.init_hidden()
prime_input = char_tensor(prime_str)
predicted = prime_str
target_meter = "1010101010"
target_rhyme = ""
# Use priming string to "build up" hidden state
for p in range(len(prime_str) - 1):
_, hidden = decoder(prime_input[p], hidden)
inp = prime_input[-1]
count = 0
while predicted.count("\n") < predict_len:
count = count + 1
output, hidden = decoder(inp, hidden)
# Sample from the network as a multinomial distribution
output_dist = output.data.view(-1).div(temperature).exp()
top_i = torch.multinomial(output_dist, 1)[0]
# max_prob = 0.0
# top_i = 0
# for j in range(len(output_dist)):
# if output_dist[j] > max_prob:
# max_prob = output_dist[j]
# top_i = j
# Add predicted character to string and use as next input
predicted_char = vocab[top_i]
while predicted_char.strip() == "":
# output_dist[top_i] = 0.0
# max_prob = 0.0
# top_i = 0
# for j in range(len(output_dist)):
# if output_dist[j] > max_prob:
# max_prob = output_dist[j]
# top_i = j
top_i = torch.multinomial(output_dist, 1)[0]
predicted_char = vocab[top_i]
if predicted_char.strip() != "":
meter = True
while meter:
if pronouncing.stresses_for_word(predicted_char):
word_meter = adjusted_meter(pronouncing.stresses_for_word(predicted_char)[0])
if target_meter.startswith(word_meter):
meter = False
else:
top_i = torch.multinomial(output_dist, 1)[0]
predicted_char = vocab[top_i]
else:
top_i = torch.multinomial(output_dist, 1)[0]
predicted_char = vocab[top_i]
if pronouncing.stresses_for_word(predicted_char):
word_meter = adjusted_meter(pronouncing.stresses_for_word(predicted_char)[0])
if target_meter.startswith(word_meter):
predicted += [predicted_char]
inp = char_tensor([predicted_char])
target_meter = target_meter[len(word_meter):]
if target_meter == "":
final_word = predicted.pop()
if target_rhyme != "":
meter_candidates = pronouncing.search_stresses(pronouncing.stresses_for_word(final_word)[0])
rhyme_candidates = pronouncing.rhymes(target_rhyme)
candidates = list(set(meter_candidates) & set(rhyme_candidates) & set(vocab))
if candidates:
#candidates = [output_dist[char_tensor([candidate])] for candidate in candidates if candidate in vocab]
#print([char_tensor([candidate]) for candidate in candidates])
max_prob = 0.0
max_index = 0
for i in range(len(output_dist)):
if vocab[i] in candidates and output_dist[i] > max_prob:
max_prob = output_dist[i]
max_index = i
final_word = vocab[max_index]
predicted += [final_word, "\n"]
inp = char_tensor([final_word])
if target_rhyme == "":
target_rhyme = final_word
else:
target_rhyme = ""
target_meter = "1010101010"
elif target_meter == "0":
target_meter = "1"
#print(count)
return predicted
Quoth the Raven “Nevermore.”
And the Raven, never flitting, still is sitting, still is sitting
On the pallid bust of Pallas just above my chamber door;
And his eyes have all the seeming of a demon’s that is dreaming,
And the lamp-light o’er him streaming throws his shadow on the floor;
And my soul from out that shadow that lies floating on the floor
Shall be lifted—nevermore!"""
poem = poem.translate(str.maketrans('', '', string.punctuation))
poem = poem.translate(str.maketrans('', '', '1234567890'))
newpoem = []
for line in poem.split("\n"):
for word in poem.lower().split():
phones = pronouncing.phones_for_word(word)
if phones:
stress_list = [pronouncing.stresses(phone) for phone in phones]
search = "^" + stress_list[0] + "$"
if len(stress_list) > 1:
for stress in stress_list[1:]:
search += "$|^%s" % stress
word = random.choice(pronouncing.search_stresses(search))
else:
pass
for letter in word:
sys.stdout.write(letter)
sys.stdout.flush()
time.sleep(.1)
sys.stdout.write(" ")
sys.stdout.flush()
print("\n")
def test_search_stresses(self):
words = pronouncing.search_stresses("^000100$")
self.assertEqual(words, ["phytogeography", "uninterruptible", "uninterruptible", "variability"])
words = pronouncing.search_stresses("^[12]0[12]0[12]0[12]$")
self.assertEqual(words, ["dideoxycytidine", "homosexuality", "hypersensitivity"])