liudiao1992
commented
6 months ago text/chinese.py
def _g2p(segments): phones_list = [] word2ph = [] for seg in segments: pinyins = []
Replace all English words in the sentence
seg = re.sub("[a-zA-Z]+", "", seg)
seg_cut = psg.lcut(seg)
initials = []
finals = []
seg_cut = tone_modifier.pre_merge_for_modify(seg_cut)
for word, pos in seg_cut:
if pos == "eng":
continue
sub_initials, sub_finals = _get_initials_finals(word)
sub_finals = tone_modifier.modified_tone(word, pos, sub_finals)
initials.append(sub_initials)
finals.append(sub_finals)
# assert len(sub_initials) == len(sub_finals) == len(word)
initials = sum(initials, [])
finals = sum(finals, [])
# region 在这里进行读音的修改 2表示这句话第3个字，ni3表示读音
# initial,final = split_pinyin_initial_final('ni3')
# initials[2] = initial
# finals[2] = final
print(initials, finals)
#
for c, v in zip(initials, finals):
raw_pinyin = c + v
# NOTE: post process for pypinyin outputs
# we discriminate i, ii and iii
if c == v:
assert c in punctuation
phone = [c]
word2ph.append(1)
else:
v_without_tone = v[:-1]
tone = v[-1]
pinyin = c + v_without_tone
assert tone in "12345"
if c:
# 多音节
v_rep_map = {
"uei": "ui",
"iou": "iu",
"uen": "un",
}
if v_without_tone in v_rep_map.keys():
pinyin = c + v_rep_map[v_without_tone]
else:
# 单音节
pinyin_rep_map = {
"ing": "ying",
"i": "yi",
"in": "yin",
"u": "wu",
}
if pinyin in pinyin_rep_map.keys():
pinyin = pinyin_rep_map[pinyin]
else:
single_rep_map = {
"v": "yu",
"e": "e",
"i": "y",
"u": "w",
}
if pinyin[0] in single_rep_map.keys():
pinyin = single_rep_map[pinyin[0]] + pinyin[1:]
assert pinyin in pinyin_to_symbol_map.keys(), (pinyin, seg, raw_pinyin)
new_c, new_v = pinyin_to_symbol_map[pinyin].split(" ")
new_v = new_v + tone
phone = [new_c, new_v]
word2ph.append(len(phone))
phones_list += phone
return phones_list, word2ph修改多音字读音的方法，具体实现可以自己修改
uone-1
这样很多情况下可以自定义 不用等更新 更进一步可以共享读取自定义多音字文件 比如说粗话 操字 一般要读4音 另外很多繁体字 比如 “着”都写作“著” 惯用字写法读音和大陆不一样