def __extract_feature(new_lines, poly_dict):
data_lines = []
meta_data = []
for line in new_lines:
line = rm_prosody(line)
line = re.sub(u"\\(.*?\\)|\\{.*?}|\\[.*?]", "", line)
phone, chars = line.split("|")[1], line.split("|")[2]
chars = clean_sentence(chars.replace(" ", ""))
# phone = split_tone(phone)
try:
phone_pairs = phone2pairs(chars, phone)
new_phone_pairs = []
for c, p in phone_pairs:
if c in poly_dict.keys():
new_phone_pairs.append((c, p))
else:
new_phone_pairs.append((c, "-"))
data_lines.append(line)
meta_data.append(([p for p in chars],
[p.replace(" ", "").replace("*", "")
for _, p in new_phone_pairs]))
except TypeError:
pass
except IndexError:
print("Index Error:", phone, chars)
print("there are {} trainable lines".format(len(data_lines)))
for i in range(5):
print(meta_data[i])
data_x = [x for x, _ in meta_data]
data_y = [y for _, y in meta_data]
return data_x, data_y, data_lines
def __generate_simple_poly_dict():
data_path = '/data1/liujshi/yunlv_research/total_zhuiyi_corup/' \
'total_metadata_new'
total_lines = read_lines(data_path)[0:]
print(total_lines[0:5])
total_dict, poly_dict = defaultdict(list), defaultdict(list)
for line in total_lines:
phone, chars = line.split("|")[1], line.split("|")[2]
chars = clean_sentence(chars.replace(" ", ""))
phone = __change_tone_format(phone)
try:
phone_pairs = phone2pairs(chars, phone)
for c, p in phone_pairs:
total_dict[c].append(p)
total_dict[c] = list(set(total_dict[c]))
except TypeError:
pass
except IndexError:
print("Index Error:", phone, chars)
for line in read_lines("../../other_files/poly_dict"):
key = line.split(":")[0]
value = line.split(":")[1].split(",")
poly_dict[key] = value
map_phone = dict()
for line in read_lines("../../other_files/phone_map_merge.txt"):
key = line.split(":")[0]
value = line.split(":")[1]
map_phone[key] = value
new_lines = []
for char in poly_dict.keys():
if char not in total_dict.keys():
pass # 未出现过的多音字移除掉
else:
values = total_dict[char]
value_saved = []
for value in values:
# 发音词典拼音转化成标准拼音进行比对。
map_value = map_phone[value.split()[0]] + \
map_phone[value.split()[1] + value.split()[2][-1]]
if map_value in poly_dict[char]:
value_saved.append(value)
if len(value_saved) > 1:
new_line = "{}:{}".format(char, ",".join(value_saved))
new_lines.append(new_line)
print("save:", new_line)
else:
pass # 只出现过其中一个音的多音字移除掉。
write_lines("../../other_files/simple_poly_dict", new_lines)
return None
def main():
model_dir = "/data1/liufeng/synthesis/frontend/models/psd_v1"
eval_dir = os.path.join(model_dir, "eval")
os.makedirs(eval_dir, exist_ok=True)
# data_path = os.path.join(model_dir, "metadata_dev.txt")
data_path = "/data1/liufeng/synthesis/feature/feature_taco/feat_0307/" \
"dev_psd.txt"
metadata = read_lines(data_path)
print(metadata[0:2])
text_path = os.path.join(eval_dir, "corpus.txt")
corpus = [
rm_prosody(line.split("|")[6].replace(" ", "")).upper()
for line in metadata
]
write_lines(text_path, corpus)
sub_count = 0
# truth_path = "output.txt"
truth_path = os.path.join(eval_dir, "truth.txt")
with open(truth_path, "w", encoding="utf-8") as fr:
for sent_id, meta in enumerate(metadata):
phone = (meta.split("|")[5])
sentence = clean_sentence(
meta.split("|")[6].replace(" ", "").upper())
fr.write("\nid:{}\n{}\n".format(sent_id, sentence))
print("\nid:{}\n{}".format(sent_id, sentence))
sub_sentences = split_sentence(sentence)
sub_phones = split_sentence(phone, split_type="phone")
for split_id, (sent,
phone) in enumerate(zip(sub_sentences, sub_phones)):
fr.write("split-id:{} | {}\n{}\n".format(
split_id, sent, phone))
print("split-id:{} | {} | {}".format(split_id, sent, phone))
sub_count += 1
fr.write("split-end\n")
print("\nsub count:{}".format(sub_count))
print("write other_files to {}".format(truth_path))
def main():
model_dir = "/data1/liufeng/synthesis/frontend/models/v3"
eval_dir = os.path.join(model_dir, "eval")
os.makedirs(eval_dir, exist_ok=True)
data_path = os.path.join(model_dir, "metadata_dev.txt")
metadata = read_lines(data_path)
print(metadata[0])
text_path = os.path.join(eval_dir, "corpus.txt")
corpus = [
rm_prosody(line.split("|")[2].replace(" ", "")).upper()
for line in metadata
]
print(corpus[0])
write_lines(text_path, corpus)
sub_count = 0
truth_path = os.path.join(eval_dir, "truth.txt")
with open(truth_path, "w", encoding="utf-8") as fr:
for sent_id, meta in enumerate(metadata):
meta = rm_prosody(meta)
sentence, phone = meta.split("|")[2].replace(
" ", ""), meta.split("|")[1]
sentence = clean_sentence(sentence).upper()
print(sentence)
fr.write("\nid:{}\n{}\n".format(sent_id, sentence))
print("\nid:{}\n{}".format(sent_id, sentence))
sub_sentences = split_sentence(sentence)
sub_phones = split_sentence(phone, split_type="phone")
for split_id, (sent,
phone) in enumerate(zip(sub_sentences, sub_phones)):
fr.write("split-id:{} | {}\n{}\n".format(
split_id, sent, phone))
print("split-id:{} | {} | {}".format(split_id, sent, phone))
sub_count += 1
fr.write("split-end\n")
print("\nsub count:{}".format(sub_count))
print("write files to {}".format(truth_path))
def __compute_psd_result(hparams, sentences, load_memory=False):
from src.model.prosody import BertProsody
psd_predict = BertProsody()
bert_result_path = os.path.join(hparams.psd_model_dir, "bert_result.pkl")
if os.path.exists(bert_result_path) and load_memory:
with open(bert_result_path, "rb") as fr:
bert_psd_result = pickle.load(fr)
else:
bert_input = []
for sent_id, sentence in enumerate(sentences):
sentence = clean_sentence(sentence)
sub_sentences = split_sentence(sentence)
bert_input.extend(sub_sentences)
model_path, init_epoch = get_model_path(
os.path.join(hparams.psd_model_dir, "hdf5"))
psd_predict.initial_model(bert_model_path=hparams.bert_model_path,
psd_model_path=model_path)
bert_psd_result = psd_predict.predict(bert_input)
with open(bert_result_path, "wb") as fw:
pickle.dump(bert_psd_result, fw)
print("completed bert inference")
return psd_predict, bert_psd_result
def __compute_nnet_phone_result(hparams, sentences, load_memory=False):
from src.model.phone import BertPolyPhone
phone_predictor = BertPolyPhone()
bert_result_path = os.path.join(hparams.poly_model_dir, "bert_result.pkl")
if os.path.exists(bert_result_path) and load_memory:
with open(bert_result_path, "rb") as fr:
bert_phone_result = pickle.load(fr)
else:
bert_input = []
for sent_id, sentence in enumerate(sentences):
sentence = clean_sentence(sentence)
sub_sentences = split_sentence(sentence)
bert_input.extend(sub_sentences)
print("total sub sentences:{}".format(len(bert_input)))
model_path, init_epoch = get_model_path(
os.path.join(hparams.poly_model_dir, "hdf5"))
phone_predictor.inialize_model(bert_model_path=hparams.bert_model_path,
poly_model_path=model_path)
bert_phone_result = phone_predictor.predict(bert_input)
with open(bert_result_path, "wb") as fw:
pickle.dump(bert_phone_result, fw)
print("completed bert inference")
return phone_predictor, bert_phone_result
def main():
model_dir = "/data1/liufeng/synthesis/frontend/models/v2"
eval_dir = os.path.join(model_dir, "eval")
os.makedirs(eval_dir, exist_ok=True)
# data_path = os.path.join(model_dir, "metadata_dev.txt")
data_path = "/data1/liufeng/synthesis/feature/feature_prosody/" \
"bzn/dev.txt"
metadata = read_lines(data_path)
print(metadata[0:2])
# dev_corpus = [line.split("|")[6] for line in read_lines(data_path)]
# dev_phones = [line.split("|")[5] for line in read_lines(data_path)]
# print(dev_corpus[0])
# line = dev_corpus[0]
# x, y = split_psd(line)
# print(x, y)
#
# exit()
# metadata = [line for line in metadata if "bzn" in line]
# print(metadata[0:3])
text_path = os.path.join(eval_dir, "corpus.txt")
corpus = [
rm_prosody(line.split("|")[6].replace(" ", "")) for line in metadata
]
# print(corpus[0:3])
write_lines(text_path, corpus)
# exit()
sub_count = 0
# truth_path = os.path.join(eval_dir, "bc_dev.txt")
truth_path = "output.txt"
with open(truth_path, "w", encoding="utf-8") as fr:
for sent_id, meta in enumerate(metadata):
phone = (meta.split("|")[5])
sentence = clean_sentence(meta.split("|")[6].replace(" ", ""))
_ss = sentence
print(phone, sentence)
# x, y = split_psd(sentence)
# sentence = "".join(x)
# assert len(y) == len(sentence)
# if not check_exist_eng(sentence):
# continue
fr.write("\nid:{}\n{}\n".format(sent_id, _ss))
print("\nid:{}\n{}".format(sent_id, _ss))
sub_sentences = split_sentence(sentence)
sub_phones = split_sentence(phone, split_type="phone")
# print(len(y), len(sub_phones), len(sub_sentences))
for split_id, (sent,
phone) in enumerate(zip(sub_sentences, sub_phones)):
x, y = split_psd(sent)
sent = "".join(x)
print(sent, phone)
pairs = phone2pairs(sent, phone)
new_pairs = [(_x[0], _x[1], _y) for _x, _y in zip(pairs, y)]
new_phone = [_y + " #" + _z for _x, _y, _z in new_pairs]
new_phone = " ".join(new_phone).replace(" #0", "")
fr.write("split-id:{} | {}\n{}\n".format(
split_id, sent, new_phone))
print("split-id:{} | {} | {}".format(split_id, sent,
new_phone))
sub_count += 1
fr.write("split-end\n")
# exit()
print("\nsub count:{}".format(sub_count))
print("write other_files to {}".format(truth_path))