File size: 2,358 Bytes
83d190a
 
2916d61
83d190a
 
 
 
 
 
 
 
2916d61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83d190a
2916d61
83d190a
 
2916d61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83d190a
2916d61
 
83d190a
2916d61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83d190a
2916d61
83d190a
 
 
 
2916d61
83d190a
 
2916d61
83d190a
 
 
2916d61
83d190a
 
2916d61
83d190a
 
2916d61
 
83d190a
2916d61
83d190a
 
2916d61
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
# Punctuations
PUNCTUATIONS = ["!", "?", "…", ",", ".", "'", "-"]

# Punctuations and special tokens
PUNCTUATION_SYMBOLS = PUNCTUATIONS + ["SP", "UNK"]

# Padding
PAD = "_"

# Chinese symbols
ZH_SYMBOLS = [
    "E",
    "En",
    "a",
    "ai",
    "an",
    "ang",
    "ao",
    "b",
    "c",
    "ch",
    "d",
    "e",
    "ei",
    "en",
    "eng",
    "er",
    "f",
    "g",
    "h",
    "i",
    "i0",
    "ia",
    "ian",
    "iang",
    "iao",
    "ie",
    "in",
    "ing",
    "iong",
    "ir",
    "iu",
    "j",
    "k",
    "l",
    "m",
    "n",
    "o",
    "ong",
    "ou",
    "p",
    "q",
    "r",
    "s",
    "sh",
    "t",
    "u",
    "ua",
    "uai",
    "uan",
    "uang",
    "ui",
    "un",
    "uo",
    "v",
    "van",
    "ve",
    "vn",
    "w",
    "x",
    "y",
    "z",
    "zh",
    "AA",
    "EE",
    "OO",
]
NUM_ZH_TONES = 6

# Japanese
JP_SYMBOLS = [
    "N",
    "a",
    "a:",
    "b",
    "by",
    "ch",
    "d",
    "dy",
    "e",
    "e:",
    "f",
    "g",
    "gy",
    "h",
    "hy",
    "i",
    "i:",
    "j",
    "k",
    "ky",
    "m",
    "my",
    "n",
    "ny",
    "o",
    "o:",
    "p",
    "py",
    "q",
    "r",
    "ry",
    "s",
    "sh",
    "t",
    "ts",
    "ty",
    "u",
    "u:",
    "w",
    "y",
    "z",
    "zy",
]
NUM_JP_TONES = 2

# English
EN_SYMBOLS = [
    "aa",
    "ae",
    "ah",
    "ao",
    "aw",
    "ay",
    "b",
    "ch",
    "d",
    "dh",
    "eh",
    "er",
    "ey",
    "f",
    "g",
    "hh",
    "ih",
    "iy",
    "jh",
    "k",
    "l",
    "m",
    "n",
    "ng",
    "ow",
    "oy",
    "p",
    "r",
    "s",
    "sh",
    "t",
    "th",
    "uh",
    "uw",
    "V",
    "w",
    "y",
    "z",
    "zh",
]
NUM_EN_TONES = 4

# Combine all symbols
NORMAL_SYMBOLS = sorted(set(ZH_SYMBOLS + JP_SYMBOLS + EN_SYMBOLS))
SYMBOLS = [PAD] + NORMAL_SYMBOLS + PUNCTUATION_SYMBOLS
SIL_PHONEMES_IDS = [SYMBOLS.index(i) for i in PUNCTUATION_SYMBOLS]

# Combine all tones
NUM_TONES = NUM_ZH_TONES + NUM_JP_TONES + NUM_EN_TONES

# Language maps
LANGUAGE_ID_MAP = {"ZH": 0, "JP": 1, "EN": 2}
NUM_LANGUAGES = len(LANGUAGE_ID_MAP.keys())

# Language tone start map
LANGUAGE_TONE_START_MAP = {
    "ZH": 0,
    "JP": NUM_ZH_TONES,
    "EN": NUM_ZH_TONES + NUM_JP_TONES,
}


if __name__ == "__main__":
    a = set(ZH_SYMBOLS)
    b = set(EN_SYMBOLS)
    print(sorted(a & b))