Hugging Face's logo

Spaces:
project-ori
/
AronaTTS
Runtime error

App Files Community
1
AronaTTS
File size: 2,046 Bytes 
35b8bdf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d9e50d0
35b8bdf
 
 
 
 
 
 
 
 
d9e50d0
35b8bdf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
 
from text.cleaners import japanese_to_romaji_with_accent
from text.korean import (
    join_jamos, j2hcj, h2j,
    latin_to_hangul,
    number_to_hangul,
    g2pk,
)
import re
import jaconv


repl_lst = {
    'γ„²': 'γ…‹',
    'γ„Έ': 'γ…Œ',
    'γ…ƒ': 'ㅍ',
    'γ…†': 'γ……',
    'γ…‰': 'γ…Š',
    
    'γ…™': 'γ…—/γ…”',
    'γ…š': 'γ…—/γ…£',
    'γ…˜': 'γ…œγ…',
    'ㅝ': 'γ…œ/γ…“',
    'γ…ž': 'γ…œ/γ…”',
    'γ…Ÿ': 'γ…œγ…£',
    'γ…’': 'γ…œγ…£',

    'γ…’': 'γ…£γ…”',
    'γ…•': 'γ…›',
    'γ…–': 'γ…£γ…”',

    'γ…“': 'γ…—',
    'ㅐ': 'γ…”',
    'γ…‘': 'γ…œ',

    '||//γ…Ž': 'γ„Ή',
}


def get_word_list(text):
    text = g2pk(text)
    text = latin_to_hangul(text)
    text = number_to_hangul(text)
    text = j2hcj(h2j(text))
    text = re.sub(r'([\u3131-\u3163])$', r'\1.', text)
    return list(join_jamos(text.replace('  ', ' ')[:-1]))


def korean2katakana(text):
    word_lst = get_word_list(text)
    text = '/' + text.replace('/', ' ').replace('|', ' ').replace('^', ' ').replace('  ', ' ').replace(' ', '^')
    new_lst = []

    for i, s in enumerate(word_lst):
        dh = list(j2hcj(h2j(s)))
        if len(dh) == 3:
            if dh[-1] == 'γ„΄':
                dh[-1] = 'γ„΄'
                
            elif dh[-1] == 'ㅁ' or dh[-1] == 'γ…‡':
                dh[-1] = 'γ„΄|'
            
            elif dh[-1] == 'γ„Ή':
                dh[-1] = '||/'

            else: # γ„± γ„· γ…‚
                dh[-1] = dh[-1]

        
        dh.append('/')
        new_lst.extend(dh)

    kr = ''.join(new_lst)
    
    for k, v in repl_lst.items():
        kr = kr.replace(k, v)
    kr2ro = japanese_to_romaji_with_accent(kr).replace('si', 'shi').replace('c', 'ts') \
                                              .replace('ti', 'ティー').replace('tu', 'γƒˆγ‚₯γƒΌ') \
                                              .replace('di', 'ディー').replace('du', 'ドγ‚₯γƒΌ')
    result = jaconv.alphabet2kata(kr2ro)
    result = result.replace('/', '').replace('|', 'γƒΌ').replace('^', '')
    print(result)
    return result