File size: 4,464 Bytes
a71e647
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c105fbb
 
a71e647
c105fbb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a71e647
c105fbb
 
 
a71e647
c105fbb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a71e647
 
 
 
c105fbb
a71e647
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
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
# Language dict
language_code_to_name = {
    "afr": "Afrikaans",
    "amh": "Amharic",
    "arb": "Modern Standard Arabic",
    "ary": "Moroccan Arabic",
    "arz": "Egyptian Arabic",
    "asm": "Assamese",
    "ast": "Asturian",
    "azj": "North Azerbaijani",
    "bel": "Belarusian",
    "ben": "Bengali",
    "bos": "Bosnian",
    "bul": "Bulgarian",
    "cat": "Catalan",
    "ceb": "Cebuano",
    "ces": "Czech",
    "ckb": "Central Kurdish",
    "cmn": "Mandarin Chinese",
    "cym": "Welsh",
    "dan": "Danish",
    "deu": "German",
    "ell": "Greek",
    "eng": "English",
    "est": "Estonian",
    "eus": "Basque",
    "fin": "Finnish",
    "fra": "French",
    "gaz": "West Central Oromo",
    "gle": "Irish",
    "glg": "Galician",
    "guj": "Gujarati",
    "heb": "Hebrew",
    "hin": "Hindi",
    "hrv": "Croatian",
    "hun": "Hungarian",
    "hye": "Armenian",
    "ibo": "Igbo",
    "ind": "Indonesian",
    "isl": "Icelandic",
    "ita": "Italian",
    "jav": "Javanese",
    "jpn": "Japanese",
    "kam": "Kamba",
    "kan": "Kannada",
    "kat": "Georgian",
    "kaz": "Kazakh",
    "kea": "Kabuverdianu",
    "khk": "Halh Mongolian",
    "khm": "Khmer",
    "kir": "Kyrgyz",
    "kor": "Korean",
    "lao": "Lao",
    "lit": "Lithuanian",
    "ltz": "Luxembourgish",
    "lug": "Ganda",
    "luo": "Luo",
    "lvs": "Standard Latvian",
    "mai": "Maithili",
    "mal": "Malayalam",
    "mar": "Marathi",
    "mkd": "Macedonian",
    "mlt": "Maltese",
    "mni": "Meitei",
    "mya": "Burmese",
    "nld": "Dutch",
    "nno": "Norwegian Nynorsk",
    "nob": "Norwegian Bokm\u00e5l",
    "npi": "Nepali",
    "nya": "Nyanja",
    "oci": "Occitan",
    "ory": "Odia",
    "pan": "Punjabi",
    "pbt": "Southern Pashto",
    "pes": "Western Persian",
    "pol": "Polish",
    "por": "Portuguese",
    "ron": "Romanian",
    "rus": "Russian",
    "slk": "Slovak",
    "slv": "Slovenian",
    "sna": "Shona",
    "snd": "Sindhi",
    "som": "Somali",
    "spa": "Spanish",
    "srp": "Serbian",
    "swe": "Swedish",
    "swh": "Swahili",
    "tam": "Tamil",
    "tel": "Telugu",
    "tgk": "Tajik",
    "tgl": "Tagalog",
    "tha": "Thai",
    "tur": "Turkish",
    "ukr": "Ukrainian",
    "urd": "Urdu",
    "uzn": "Northern Uzbek",
    "vie": "Vietnamese",
    "xho": "Xhosa",
    "yor": "Yoruba",
    "yue": "Cantonese",
    "zlm": "Colloquial Malay",
    "zsm": "Standard Malay",
    "zul": "Zulu",
}
LANGUAGE_NAME_TO_CODE = {v: k for k, v in language_code_to_name.items()}

# Source langs: S2ST / S2TT / ASR don't need source lang
# T2TT / T2ST use this
text_source_language_codes = [
    "afr",
    "amh",
    "arb",
    "ary",
    "arz",
    "asm",
    "azj",
    "bel",
    "ben",
    "bos",
    "bul",
    "cat",
    "ceb",
    "ces",
    "ckb",
    "cmn",
    "cym",
    "dan",
    "deu",
    "ell",
    "eng",
    "est",
    "eus",
    "fin",
    "fra",
    "gaz",
    "gle",
    "glg",
    "guj",
    "heb",
    "hin",
    "hrv",
    "hun",
    "hye",
    "ibo",
    "ind",
    "isl",
    "ita",
    "jav",
    "jpn",
    "kan",
    "kat",
    "kaz",
    "khk",
    "khm",
    "kir",
    "kor",
    "lao",
    "lit",
    "lug",
    "luo",
    "lvs",
    "mai",
    "mal",
    "mar",
    "mkd",
    "mlt",
    "mni",
    "mya",
    "nld",
    "nno",
    "nob",
    "npi",
    "nya",
    "ory",
    "pan",
    "pbt",
    "pes",
    "pol",
    "por",
    "ron",
    "rus",
    "slk",
    "slv",
    "sna",
    "snd",
    "som",
    "spa",
    "srp",
    "swe",
    "swh",
    "tam",
    "tel",
    "tgk",
    "tgl",
    "tha",
    "tur",
    "ukr",
    "urd",
    "uzn",
    "vie",
    "yor",
    "yue",
    "zsm",
    "zul",
]
TEXT_SOURCE_LANGUAGE_NAMES = sorted([language_code_to_name[code] for code in text_source_language_codes])

# Target langs:
# S2ST / T2ST
s2st_target_language_codes = [
    "eng",
    "arb",
    "ben",
    "cat",
    "ces",
    "cmn",
    "cym",
    "dan",
    "deu",
    "est",
    "fin",
    "fra",
    "hin",
    "ind",
    "ita",
    "jpn",
    "kor",
    "mlt",
    "nld",
    "pes",
    "pol",
    "por",
    "ron",
    "rus",
    "slk",
    "spa",
    "swe",
    "swh",
    "tel",
    "tgl",
    "tha",
    "tur",
    "ukr",
    "urd",
    "uzn",
    "vie",
]
S2ST_TARGET_LANGUAGE_NAMES = sorted([language_code_to_name[code] for code in s2st_target_language_codes])

# S2TT / ASR
S2TT_TARGET_LANGUAGE_NAMES = TEXT_SOURCE_LANGUAGE_NAMES
# T2TT
T2TT_TARGET_LANGUAGE_NAMES = TEXT_SOURCE_LANGUAGE_NAMES