Hugging Face's logo

Spaces:
Eripsa
/
basque-asr-space
Sleeping

App Files Community
basque-asr-space
File size: 2,727 Bytes 
c27990f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
 
from ipapy import UNICODE_TO_IPA
from ipapy.ipachar import IPAChar


SYMBOLS = {
    "r": 1,
    "ʝ": 2,
    "ã": 3,
    "gː": 4,
    "t": 5,
    "n": 6,
    "w": 7,
    "u": 8,
    "l": 9,
    "yː": 10,
    "ʎ": 11,
    "bʲ": 12,
    "ə": 13,
    "ʃʲ": 14,
    "sː": 15,
    "zʲ": 16,
    "kː": 17,
    "y": 18,
    "ɒ": 19,
    "fʲ": 20,
    "ɑ": 21,
    "ʏ": 22,
    "ɣ": 23,
    "s": 24,
    "m": 25,
    "tː": 26,
    "xʲ": 27,
    "vː": 28,
    "ø": 29,
    "h": 30,
    "ɨ": 31,
    "dʲ": 32,
    "dː": 33,
    "bː": 34,
    "ɲː": 35,
    "ɑː": 36,
    "ɪ": 37,
    "ɛ": 38,
    "i": 39,
    "ʔ": 40,
    "g": 41,
    "ʃ": 42,
    "ɜː": 43,
    "mː": 44,
    "øː": 45,
    "fː": 46,
    "p": 47,
    "iː": 48,
    "(...)": 49,
    "v": 50,
    "ʌ": 51,
    "b": 52,
    "k": 53,
    "x": 54,
    "ɲ": 55,
    "ʒ": 56,
    "rː": 57,
    "eː": 58,
    "ç": 59,
    "ŋ": 60,
    "ɔː": 61,
    "œ": 62,
    "ẽ": 63,
    "θ": 64,
    "a": 65,
    "rʲ": 66,
    "vʲ": 67,
    "ʃː": 68,
    "æ": 69,
    "ɶ̃": 70,
    "pː": 71,
    "nː": 72,
    "lʲ": 73,
    "õ": 74,
    "pʲ": 75,
    "ɱ": 76,
    "ð": 77,
    "f": 78,
    "j": 79,
    "o": 80,
    "nʲ": 81,
    "sʲ": 82,
    "lː": 83,
    "e": 84,
    "d": 85,
    "ʊ": 86,
    "gʲ": 87,
    "z": 88,
    "ɛː": 89,
    "tʲ": 90,
    "β": 91,
    "mʲ": 92,
    "uː": 93,
    "ɥ": 94,
    "ʀ": 95,
    "aː": 96,
    "ɐ": 97,
    "ɔ": 98,
    "oː": 99,
    "ʎː": 100,
    "kʲ": 101
}

DESCRIPTORS = {}
for s in SYMBOLS:
        desc = []
        if s == "(...)":
            DESCRIPTORS[s] = "silence"
            continue
        else:
            for sym in s:
                desc.extend(UNICODE_TO_IPA[sym].descriptors)
        if "suprasegmental" in desc:
            desc.remove("suprasegmental")
        if "diacritic" in desc:
            desc.remove("diacritic")
        x = IPAChar(desc)
        DESCRIPTORS[s] = x.canonical_representation


def to_index(symbol: str, elongations=True) -> int:
    if not elongations:
        symbol = symbol.replace('ː', '')
    return SYMBOLS[symbol]


def to_symbol(index: int, elongations=True) -> str:
    idx = list(SYMBOLS.values()).index(index)
    symbol = list(SYMBOLS.keys())[idx] if elongations else list(SYMBOLS.keys())[idx].replace('ː', '')
    return symbol


def get_class_count() -> int:
    return max(SYMBOLS.values())


def symbol_to_descriptor(symbol: str) -> str:
    return DESCRIPTORS[symbol]


def index_to_descriptor(index: int) -> str:
    return DESCRIPTORS[to_symbol(index)]


if __name__ == "__main__":
    print("Running phonetics internal tests")
    for s in SYMBOLS:
        print(f"{s}: {DESCRIPTORS[s]}")