def rhymecheck(w1, w2):
w1 = g2p.runKoG2P(w1, 'rulebook.txt')
w2 = g2p.runKoG2P(w2, 'rulebook.txt')
w1 = w1.split()
w2 = w2.split()
#print('변환하기 전의 음운 구성')
#print(w1)
#print(w2)
w1 = vowelconvt(w1)
w2 = vowelconvt(w2)
w1 = conconvt(w1)
w2 = conconvt(w2)
#print('변환 후의 음운 구성')
#print(w1)
#print(w2)
lcs_res = lcs_length(w1, w2)/(max(len(w1), len(w2)))
#print("전체 단어의 최장 겹침 수 : " + str(lcs_res))
res = lcs_res
return res
def _normalize(line):
_, expanded, text = line.strip().split("|")
if hp.num_exp == 0:
text = expanded + u"␃" # ␃: EOS
text = runKoG2P(text, "rulebook.txt")
else:
text += u"␃"
if hp.num_exp == 2:
text = [j2hcj[char] for char in text]
elif hp.num_exp == 3:
text = [j2sj[char] for char in text]
elif hp.num_exp == 4:
text = [j2shcj[char] for char in text]
text = chain.from_iterable(text)
text = [char2idx[char] for char in text]
return text
def load_data(mode="train"):
'''Loads data
Args:
mode: "train" or "synthesize".
'''
# Load vocabulary
char2idx, idx2char = load_vocab()
# load conversion dictionaries
j2hcj, j2sj, j2shcj = load_j2hcj(), load_j2sj(), load_j2shcj()
if mode == "train":
# Parse
fpaths, text_lengths, texts = [], [], []
transcript = os.path.join(hp.data, 'transcript.v.1.1.txt')
lines = codecs.open(transcript, 'rb', 'utf-8').readlines()
for line in lines:
fname, _, expanded, text, _ = line.strip().split("|")
fpath = os.path.join(hp.data, fname)
fpaths.append(fpath)
if hp.num_exp == 0:
text = expanded + u"␃" # ␃: EOS
text = runKoG2P(text, "rulebook.txt")
else:
text += u"␃" # ␃: EOS
if hp.num_exp == 2:
text = [j2hcj[char] for char in text]
elif hp.num_exp == 3:
text = [j2sj[char] for char in text]
elif hp.num_exp == 4:
text = [j2shcj[char] for char in text]
text = chain.from_iterable(text)
text = [char2idx[char] for char in text]
text_lengths.append(len(text))
texts.append(np.array(text, np.int32).tostring())
return fpaths, text_lengths, texts
else: # synthesize on unseen test text.
# Parse
def _normalize(line):
_, expanded, text = line.strip().split("|")
if hp.num_exp == 0:
text = expanded + u"␃" # ␃: EOS
text = runKoG2P(text, "rulebook.txt")
else:
text += u"␃"
if hp.num_exp == 2:
text = [j2hcj[char] for char in text]
elif hp.num_exp == 3:
text = [j2sj[char] for char in text]
elif hp.num_exp == 4:
text = [j2shcj[char] for char in text]
text = chain.from_iterable(text)
text = [char2idx[char] for char in text]
return text
lines = codecs.open(hp.test_data, 'rb', 'utf8').read().splitlines()
sents = [_normalize(line) for line in lines[1:]]
texts = np.zeros((len(sents), hp.max_N), np.int32)
for i, sent in enumerate(sents):
texts[i, :len(sent)] = sent
return texts
lcs_res = lcs_length(w1, w2)/(max(len(w1), len(w2)))
print("전체 단어의 최장 겹침 수 : " + str(lcs_res))
res = lcs_res
if res>=0.35:
flag=1
if flag==r[2].value:
cnt=cnt+1
flag=0
print("총 맞힌 횟수 : "+ str(cnt))
print("정확률 : "+ str(cnt/100))
'''
w1 = input()
w2 = input()
w1 = g2p.runKoG2P(w1, 'rulebook.txt')
w2 = g2p.runKoG2P(w2, 'rulebook.txt')
w1 = w1.split()
w2 = w2.split()
print('변환하기 전의 음운 구성')
print(w1)
print(w2)
w1 = vowelconvt(w1)
w2 = vowelconvt(w2)
w1 = conconvt(w1)
w2 = conconvt(w2)
print('변환 후의 음운 구성')
print(w1)
print(w2)
lcs_res = lcs_length(w1, w2) / (max(len(w1), len(w2)))
print("전체 단어의 최장 겹침 수 : " + str(lcs_res))
without_blank = []
without_blank_index = []
for index, item in enumerate(total_output_prob_sm_[0]):
if index == 0:
continue
if np.argmax(item) != 111 and np.argmax(item) != 0:
without_blank.append(item)
without_blank_index.append(index)
from g2p import runKoG2P
#estimation = total_output_prob_sm_[0]
estimation = np.asarray(without_blank)
estimation_text = vec_seq_to_kor(estimation)
gt = '베인마음속에난무얼찾아볼수있을까서투른판단에더울적해진채로보낸밤우린선을그어버릴까'
gt_phoneme = runKoG2P(gt, 'rulebook.txt')
gt_list = ''
for item in gt_phoneme.split(' '):
gt_list += Hangul[np.where(table==item)[0][0]]
gt_vec = kor_seq_to_vec(gt_list)
import numpy as np
from scipy.spatial.distance import euclidean
from fastdtw import fastdtw
distance,path = fastdtw(estimation, gt_vec, dist=euclidean)
final_timing = np.zeros(len(gt_vec),1)
