Mohamed Aymane Farhi commited on
Commit
e3a183b
1 Parent(s): 6596104

Replace language ISO codes with names.

Browse files
Files changed (3) hide show
  1. ISO_codes.json +1200 -0
  2. README.md +1 -1
  3. app.py +13 -8
ISO_codes.json ADDED
@@ -0,0 +1,1200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Abidji (abi)": "abi",
3
+ "Abkhaz (abk)": "abk",
4
+ "Ayta, Abellen (abp)": "abp",
5
+ "Achagua (aca)": "aca",
6
+ "Gikyode (acd)": "acd",
7
+ "Aceh (ace)": "ace",
8
+ "Lesser Antillean French Creole (acf)": "acf",
9
+ "Acholi (ach)": "ach",
10
+ "Achang (acn)": "acn",
11
+ "Achi (acr)": "acr",
12
+ "Achuar-Shiwiar (acu)": "acu",
13
+ "Adele (ade)": "ade",
14
+ "Jopadhola (adh)": "adh",
15
+ "Adioukrou (adj)": "adj",
16
+ "Tibetan, Amdo (adx)": "adx",
17
+ "Akeu (aeu)": "aeu",
18
+ "Afrikaans (afr)": "afr",
19
+ "Agarabi (agd)": "agd",
20
+ "Angor (agg)": "agg",
21
+ "Agutaynen (agn)": "agn",
22
+ "Awaj\u00fan (agr)": "agr",
23
+ "Awakateko (agu)": "agu",
24
+ "Aghul (agx)": "agx",
25
+ "Ahanta (aha)": "aha",
26
+ "Akha (ahk)": "ahk",
27
+ "Arosi (aia)": "aia",
28
+ "Akan (aka)": "aka",
29
+ "Batak Angkola (akb)": "akb",
30
+ "Akawaio (ake)": "ake",
31
+ "Siwu (akp)": "akp",
32
+ "Alangan (alj)": "alj",
33
+ "Alune (alp)": "alp",
34
+ "Altai, Southern (alt)": "alt",
35
+ "Alur (alz)": "alz",
36
+ "Yanesha\u2019 (ame)": "ame",
37
+ "Hamer-Banna (amf)": "amf",
38
+ "Amharic (amh)": "amh",
39
+ "Amis (ami)": "ami",
40
+ "Ambai (amk)": "amk",
41
+ "Obolo (ann)": "ann",
42
+ "Anyin (any)": "any",
43
+ "Uab Meto (aoz)": "aoz",
44
+ "Sa\u2019a (apb)": "apb",
45
+ "Arop-Lokep (apr)": "apr",
46
+ "Arabic (ara)": "ara",
47
+ "Arabela (arl)": "arl",
48
+ "Asu (asa)": "asa",
49
+ "Cishingini (asg)": "asg",
50
+ "Assamese (asm)": "asm",
51
+ "Asturian (ast)": "ast",
52
+ "Pele-Ata (ata)": "ata",
53
+ "Zaiwa (atb)": "atb",
54
+ "Ivbie North-Okpela-Arhe (atg)": "atg",
55
+ "Atti\u00e9 (ati)": "ati",
56
+ "Aralle-Tabulahan (atq)": "atq",
57
+ "Avar (ava)": "ava",
58
+ "Avatime (avn)": "avn",
59
+ "Avokaya (avu)": "avu",
60
+ "Awadhi (awa)": "awa",
61
+ "Awa (awb)": "awb",
62
+ "Ayoreo (ayo)": "ayo",
63
+ "Aymara, Central (ayr)": "ayr",
64
+ "Mai Brat (ayz)": "ayz",
65
+ "Azerbaijani, South (azb)": "azb",
66
+ "Amuzgo, San Pedro Amuzgos (azg)": "azg",
67
+ "Azerbaijani, North (azj-script_cyrillic)": "azj-script_cyrillic",
68
+ "Azerbaijani, North (azj-script_latin)": "azj-script_latin",
69
+ "Nahuatl, Highland Puebla (azz)": "azz",
70
+ "Bashkort (bak)": "bak",
71
+ "Bamanankan (bam)": "bam",
72
+ "Bali (ban)": "ban",
73
+ "Waimaha (bao)": "bao",
74
+ "Basaa (bas)": "bas",
75
+ "Vengo (bav)": "bav",
76
+ "Baatonum (bba)": "bba",
77
+ "Barai (bbb)": "bbb",
78
+ "Batak Toba (bbc)": "bbc",
79
+ "Konab\u00e9r\u00e9 (bbo)": "bbo",
80
+ "Balochi, Southern (bcc-script_arabic)": "bcc-script_arabic",
81
+ "Balochi, Southern (bcc-script_latin)": "bcc-script_latin",
82
+ "Bikol, Central (bcl)": "bcl",
83
+ "Bana (bcw)": "bcw",
84
+ "Bonggi (bdg)": "bdg",
85
+ "Baka (bdh)": "bdh",
86
+ "Bahnar (bdq)": "bdq",
87
+ "Oroko (bdu)": "bdu",
88
+ "Bodo Parja (bdv)": "bdv",
89
+ "Biali (beh)": "beh",
90
+ "Belarusian (bel)": "bel",
91
+ "Bemba (bem)": "bem",
92
+ "Bengali (ben)": "ben",
93
+ "Behoa (bep)": "bep",
94
+ "Jur Modo (bex)": "bex",
95
+ "Bari (bfa)": "bfa",
96
+ "Birifor, Malba (bfo)": "bfo",
97
+ "Bagheli (bfy)": "bfy",
98
+ "Pahari, Mahasu (bfz)": "bfz",
99
+ "Haryanvi (bgc)": "bgc",
100
+ "Bagri (bgq)": "bgq",
101
+ "Chin, Bawm (bgr)": "bgr",
102
+ "Bughotu (bgt)": "bgt",
103
+ "Bhatri (bgw)": "bgw",
104
+ "Bharia (bha)": "bha",
105
+ "Bhattiyali (bht)": "bht",
106
+ "Bada (bhz)": "bhz",
107
+ "Bisa (bib)": "bib",
108
+ "Bimoba (bim)": "bim",
109
+ "Bislama (bis)": "bis",
110
+ "Birifor, Southern (biv)": "biv",
111
+ "Binumarien (bjr)": "bjr",
112
+ "Bedjond (bjv)": "bjv",
113
+ "Bakw\u00e9 (bjw)": "bjw",
114
+ "Baruga (bjz)": "bjz",
115
+ "Binukid (bkd)": "bkd",
116
+ "Bekwarra (bkv)": "bkv",
117
+ "Kuwaa (blh)": "blh",
118
+ "Tai Dam (blt)": "blt",
119
+ "Ayta, Mag-Indi (blx)": "blx",
120
+ "Balantak (blz)": "blz",
121
+ "Bomu (bmq)": "bmq",
122
+ "Muinane (bmr)": "bmr",
123
+ "Somba-Siawari (bmu)": "bmu",
124
+ "Bum (bmv)": "bmv",
125
+ "Benga (bng)": "bng",
126
+ "Bantoanon (bno)": "bno",
127
+ "Bola (bnp)": "bnp",
128
+ "Bora (boa)": "boa",
129
+ "Tibetan, Central (bod)": "bod",
130
+ "Anjam (boj)": "boj",
131
+ "Berom (bom)": "bom",
132
+ "Bor\u00f4ro (bor)": "bor",
133
+ "Bosnian (bos)": "bos",
134
+ "Tuwuli (bov)": "bov",
135
+ "Buamu (box)": "box",
136
+ "Blaan, Koronadal (bpr)": "bpr",
137
+ "Blaan, Sarangani (bps)": "bps",
138
+ "Boko (bqc)": "bqc",
139
+ "Bakhti\u00e2ri (bqi)": "bqi",
140
+ "Bandial (bqj)": "bqj",
141
+ "Bis\u00e3 (bqp)": "bqp",
142
+ "Breton (bre)": "bre",
143
+ "Bru, Eastern (bru)": "bru",
144
+ "Oniyan (bsc)": "bsc",
145
+ "Bassa (bsq)": "bsq",
146
+ "Akoose (bss)": "bss",
147
+ "Batak Dairi (btd)": "btd",
148
+ "Batak Simalungun (bts)": "bts",
149
+ "Bete-Bendi (btt)": "btt",
150
+ "Batak Karo (btx)": "btx",
151
+ "Ntcham (bud)": "bud",
152
+ "Bulgarian (bul)": "bul",
153
+ "Bokobaru (bus)": "bus",
154
+ "Baelelea (bvc)": "bvc",
155
+ "Bauzi (bvz)": "bvz",
156
+ "Bobo Madar\u00e9, Southern (bwq)": "bwq",
157
+ "Buli (bwu)": "bwu",
158
+ "Yipma (byr)": "byr",
159
+ "Buang, Mapos (bzh)": "bzh",
160
+ "Bisu (bzi)": "bzi",
161
+ "Belize English Creole (bzj)": "bzj",
162
+ "Ch\u2019orti\u2019 (caa)": "caa",
163
+ "Garifuna (cab)": "cab",
164
+ "Chuj (cac-dialect_sanmateoixtatan)": "cac-dialect_sanmateoixtatan",
165
+ "Chuj (cac-dialect_sansebastiancoatan)": "cac-dialect_sansebastiancoatan",
166
+ "Kaqchikel (cak-dialect_central)": "cak-dialect_central",
167
+ "Kaqchikel (cak-dialect_santamariadejesus)": "cak-dialect_santamariadejesus",
168
+ "Kaqchikel (cak-dialect_santodomingoxenacoj)": "cak-dialect_santodomingoxenacoj",
169
+ "Kaqchikel (cak-dialect_southcentral)": "cak-dialect_southcentral",
170
+ "Kaqchikel (cak-dialect_western)": "cak-dialect_western",
171
+ "Kaqchikel (cak-dialect_yepocapa)": "cak-dialect_yepocapa",
172
+ "Chipaya (cap)": "cap",
173
+ "Carib (car)": "car",
174
+ "Tsiman\u00e9 (cas)": "cas",
175
+ "Catalan (cat)": "cat",
176
+ "Chiquitano (cax)": "cax",
177
+ "Carapana (cbc)": "cbc",
178
+ "Chachi (cbi)": "cbi",
179
+ "Kakataibo-Kashibo (cbr)": "cbr",
180
+ "Kashinawa (cbs)": "cbs",
181
+ "Shawi (cbt)": "cbt",
182
+ "Kandozi-Chapra (cbu)": "cbu",
183
+ "Cacua (cbv)": "cbv",
184
+ "Chopi (cce)": "cce",
185
+ "Chinantec, Comaltepec (cco)": "cco",
186
+ "Churahi (cdj)": "cdj",
187
+ "Cebuano (ceb)": "ceb",
188
+ "Chamacoco (ceg)": "ceg",
189
+ "Chin, Eastern Khumi (cek)": "cek",
190
+ "Czech (ces)": "ces",
191
+ "Chin, Falam (cfm)": "cfm",
192
+ "Kagayanen (cgc)": "cgc",
193
+ "Chechen (che)": "che",
194
+ "Chontal, Tabasco (chf)": "chf",
195
+ "Chuvash (chv)": "chv",
196
+ "Chinantec, Ozumac\u00edn (chz)": "chz",
197
+ "Ash\u00e9ninka, Pajonal (cjo)": "cjo",
198
+ "Cab\u00e9car (cjp)": "cjp",
199
+ "Shor (cjs)": "cjs",
200
+ "Kurdish, Central (ckb)": "ckb",
201
+ "Anufo (cko)": "cko",
202
+ "Chukchi (ckt)": "ckt",
203
+ "Ron (cla)": "cla",
204
+ "Chinantec, Lealao (cle)": "cle",
205
+ "Chatino, Eastern Highland (cly)": "cly",
206
+ "Cerma (cme)": "cme",
207
+ "Chinese, Mandarin (cmn-script_simplified)": "cmn-script_simplified",
208
+ "Mnong, Central (cmo-script_khmer)": "cmo-script_khmer",
209
+ "Mnong, Central (cmo-script_latin)": "cmo-script_latin",
210
+ "Mro-Khimi (cmr)": "cmr",
211
+ "Chin, Hakha (cnh)": "cnh",
212
+ "Ash\u00e1ninka (cni)": "cni",
213
+ "Chinantec, Lalana (cnl)": "cnl",
214
+ "Chinantec, Tepetotutla (cnt)": "cnt",
215
+ "Koreguaje (coe)": "coe",
216
+ "Tsafiki (cof)": "cof",
217
+ "Cora, Santa Teresa (cok)": "cok",
218
+ "Cof\u00e1n (con)": "con",
219
+ "Caquinte (cot)": "cot",
220
+ "Wamey (cou)": "cou",
221
+ "Chinantec, Palantla (cpa)": "cpa",
222
+ "Ash\u00e9ninka, Ucayali-Yur\u00faa (cpb)": "cpb",
223
+ "Ash\u00e9ninka, Pichis (cpu)": "cpu",
224
+ "Crimean Tatar (crh)": "crh",
225
+ "Cree, Plains (crk-script_latin)": "crk-script_latin",
226
+ "Cree, Plains (crk-script_syllabics)": "crk-script_syllabics",
227
+ "Cora, El Nayar (crn)": "crn",
228
+ "Chorote, Iyo\u2019wujwa (crq)": "crq",
229
+ "Seychelles French Creole (crs)": "crs",
230
+ "Chorote, Iyojwa\u2019ja (crt)": "crt",
231
+ "Jola-Kasa (csk)": "csk",
232
+ "Chinantec, Sochiapam (cso)": "cso",
233
+ "Chin, Tedim (ctd)": "ctd",
234
+ "Chittagonian (ctg)": "ctg",
235
+ "Embera Cat\u00edo (cto)": "cto",
236
+ "Chol (ctu)": "ctu",
237
+ "Chinantec, Usila (cuc)": "cuc",
238
+ "Cuiba (cui)": "cui",
239
+ "Kuna, San Blas (cuk)": "cuk",
240
+ "Kulina (cul)": "cul",
241
+ "Kabwa (cwa)": "cwa",
242
+ "Kwere (cwe)": "cwe",
243
+ "Kuwaataay (cwt)": "cwt",
244
+ "Chatino, Nopala (cya)": "cya",
245
+ "Welsh (cym)": "cym",
246
+ "Dangal\u00e9at (daa)": "daa",
247
+ "Gwahatike (dah)": "dah",
248
+ "Danish (dan)": "dan",
249
+ "Dargwa (dar)": "dar",
250
+ "Ida\u2019an (dbj)": "dbj",
251
+ "Daba (dbq)": "dbq",
252
+ "Dendi (ddn)": "ddn",
253
+ "Dedua (ded)": "ded",
254
+ "Desano (des)": "des",
255
+ "German, Standard (deu)": "deu",
256
+ "Dagaare, Southern (dga)": "dga",
257
+ "Dagara, Northern (dgi)": "dgi",
258
+ "Dagba (dgk)": "dgk",
259
+ "Dogri (dgo)": "dgo",
260
+ "Tlicho (dgr)": "dgr",
261
+ "Dhimal (dhi)": "dhi",
262
+ "Didinga (did)": "did",
263
+ "Chidigo (dig)": "dig",
264
+ "Dinka, Southwestern (dik)": "dik",
265
+ "Dinka, Northeastern (dip)": "dip",
266
+ "Maldivian (div)": "div",
267
+ "Aukan (djk)": "djk",
268
+ "Dan (dnj-dialect_blowowest)": "dnj-dialect_blowowest",
269
+ "Dan (dnj-dialect_gweetaawueast)": "dnj-dialect_gweetaawueast",
270
+ "Dani, Mid Grand Valley (dnt)": "dnt",
271
+ "Dani, Western (dnw)": "dnw",
272
+ "Lukpa (dop)": "dop",
273
+ "Dogos\u00e9 (dos)": "dos",
274
+ "Daasanach (dsh)": "dsh",
275
+ "Desiya (dso)": "dso",
276
+ "Kadazan Dusun (dtp)": "dtp",
277
+ "Dogon, Toro So (dts)": "dts",
278
+ "Chiduruma (dug)": "dug",
279
+ "Dawro (dwr)": "dwr",
280
+ "S\u00e9noufo, Djimini (dyi)": "dyi",
281
+ "Jola-Fonyi (dyo)": "dyo",
282
+ "Jula (dyu)": "dyu",
283
+ "Dzongkha (dzo)": "dzo",
284
+ "Lik (eip)": "eip",
285
+ "Ekajuk (eka)": "eka",
286
+ "Greek (ell)": "ell",
287
+ "Ember\u00e1, Northern (emp)": "emp",
288
+ "Markweeta (enb)": "enb",
289
+ "English (eng)": "eng",
290
+ "Enxet (enx)": "enx",
291
+ "Esperanto (epo)": "epo",
292
+ "Ese Ejja (ese)": "ese",
293
+ "Yupik, Saint Lawrence Island (ess)": "ess",
294
+ "Estonian (est)": "est",
295
+ "Basque (eus)": "eus",
296
+ "Evenki (evn)": "evn",
297
+ "\u00c9w\u00e9 (ewe)": "ewe",
298
+ "Ezaa (eza)": "eza",
299
+ "Fali, South (fal)": "fal",
300
+ "Faroese (fao)": "fao",
301
+ "Fataleka (far)": "far",
302
+ "Persian (fas)": "fas",
303
+ "Fijian (fij)": "fij",
304
+ "Finnish (fin)": "fin",
305
+ "Fuliiru (flr)": "flr",
306
+ "Muria, Far Western (fmu)": "fmu",
307
+ "Fon (fon)": "fon",
308
+ "French (fra)": "fra",
309
+ "Fordata (frd)": "frd",
310
+ "Frisian (fry)": "fry",
311
+ "Fulah (ful)": "ful",
312
+ "Gagauz (gag-script_cyrillic)": "gag-script_cyrillic",
313
+ "Gagauz (gag-script_latin)": "gag-script_latin",
314
+ "Mbore (gai)": "gai",
315
+ "Kandawo (gam)": "gam",
316
+ "Gadaba, Mudhili (gau)": "gau",
317
+ "Galela (gbi)": "gbi",
318
+ "Gaddi (gbk)": "gbk",
319
+ "Garhwali (gbm)": "gbm",
320
+ "Grebo, Northern (gbo)": "gbo",
321
+ "Gude (gde)": "gde",
322
+ "Kire (geb)": "geb",
323
+ "Gen (gej)": "gej",
324
+ "Kiribati (gil)": "gil",
325
+ "Gonja (gjn)": "gjn",
326
+ "Gokana (gkn)": "gkn",
327
+ "Nanai (gld)": "gld",
328
+ "Irish (gle)": "gle",
329
+ "Galician (glg)": "glg",
330
+ "Gilaki (glk)": "glk",
331
+ "Gamo (gmv)": "gmv",
332
+ "Kaansa (gna)": "gna",
333
+ "Zulgo-Gemzek (gnd)": "gnd",
334
+ "Ngangam (gng)": "gng",
335
+ "Gofa (gof-script_latin)": "gof-script_latin",
336
+ "Gogo (gog)": "gog",
337
+ "Gorontalo (gor)": "gor",
338
+ "Gor (gqr)": "gqr",
339
+ "Greek, Ancient (grc)": "grc",
340
+ "Ghari (gri)": "gri",
341
+ "Guarani (grn)": "grn",
342
+ "Garo (grt)": "grt",
343
+ "Gbaya, Southwest (gso)": "gso",
344
+ "Guajaj\u00e1ra (gub)": "gub",
345
+ "Wayuu (guc)": "guc",
346
+ "Dida, Yocobou\u00e9 (gud)": "gud",
347
+ "Guahibo (guh)": "guh",
348
+ "Gujarati (guj)": "guj",
349
+ "Gumuz (guk)": "guk",
350
+ "Misak (gum)": "gum",
351
+ "Guayabero (guo)": "guo",
352
+ "Ach\u00e9 (guq)": "guq",
353
+ "Yanomam\u00f6 (guu)": "guu",
354
+ "Gourmanch\u00e9ma (gux)": "gux",
355
+ "Wanano (gvc)": "gvc",
356
+ "Gulay (gvl)": "gvl",
357
+ "Gwich\u2019in (gwi)": "gwi",
358
+ "Gwere (gwr)": "gwr",
359
+ "Ng\u00e4bere (gym)": "gym",
360
+ "Guarayu (gyr)": "gyr",
361
+ "Hatam (had)": "had",
362
+ "Hanga (hag)": "hag",
363
+ "Chinese, Hakka (hak)": "hak",
364
+ "Hupla (hap)": "hap",
365
+ "Haitian Creole (hat)": "hat",
366
+ "Hausa (hau)": "hau",
367
+ "Haya (hay)": "hay",
368
+ "Hebrew (heb)": "heb",
369
+ "Hehe (heh)": "heh",
370
+ "Hindi, Fiji (hif)": "hif",
371
+ "Kamwe (hig)": "hig",
372
+ "Hiligaynon (hil)": "hil",
373
+ "Hindi (hin)": "hin",
374
+ "Halbi (hlb)": "hlb",
375
+ "Chin, Matu (hlt)": "hlt",
376
+ "Chhattisgarhi (hne)": "hne",
377
+ "Hanunoo (hnn)": "hnn",
378
+ "Hindustani, Sarnami (hns)": "hns",
379
+ "Ho (hoc)": "hoc",
380
+ "Holiya (hoy)": "hoy",
381
+ "Croatian (hrv)": "hrv",
382
+ "Sorbian, Upper (hsb)": "hsb",
383
+ "Witoto, Minika (hto)": "hto",
384
+ "Wamp\u00eds (hub)": "hub",
385
+ "Huli (hui)": "hui",
386
+ "Hungarian (hun)": "hun",
387
+ "Huastec (hus-dialect_centralveracruz)": "hus-dialect_centralveracruz",
388
+ "Huastec (hus-dialect_westernpotosino)": "hus-dialect_westernpotosino",
389
+ "Witoto, Murui (huu)": "huu",
390
+ "Huave, San Mateo del Mar (huv)": "huv",
391
+ "Hawu (hvn)": "hvn",
392
+ "Hawaii Pidgin (hwc)": "hwc",
393
+ "Armenian (hye)": "hye",
394
+ "Armenian, Western (hyw)": "hyw",
395
+ "Iban (iba)": "iba",
396
+ "Igbo (ibo)": "ibo",
397
+ "Islander English Creole (icr)": "icr",
398
+ "Ede Idaca (idd)": "idd",
399
+ "Ifugao, Amganad (ifa)": "ifa",
400
+ "Ifugao, Batad (ifb)": "ifb",
401
+ "If\u00e8 (ife)": "ife",
402
+ "Ifugao, Tuwali (ifk)": "ifk",
403
+ "Ifugao, Mayoyao (ifu)": "ifu",
404
+ "Kallahan, Keley-i (ify)": "ify",
405
+ "Ignaciano (ign)": "ign",
406
+ "Ika (ikk)": "ikk",
407
+ "Ila (ilb)": "ilb",
408
+ "Ilocano (ilo)": "ilo",
409
+ "Imbongu (imo)": "imo",
410
+ "Interlingua (International Auxiliary Language Association) (ina)": "ina",
411
+ "Inga (inb)": "inb",
412
+ "Indonesian (ind)": "ind",
413
+ "Tuma-Irumu (iou)": "iou",
414
+ "Ipili (ipi)": "ipi",
415
+ "Ikwo (iqw)": "iqw",
416
+ "Rigwe (iri)": "iri",
417
+ "Iraqw (irk)": "irk",
418
+ "Icelandic (isl)": "isl",
419
+ "Italian (ita)": "ita",
420
+ "Itelmen (itl)": "itl",
421
+ "Itawit (itv)": "itv",
422
+ "Ixil (ixl-dialect_sangasparchajul)": "ixl-dialect_sangasparchajul",
423
+ "Ixil (ixl-dialect_sanjuancotzal)": "ixl-dialect_sanjuancotzal",
424
+ "Ixil (ixl-dialect_santamarianebaj)": "ixl-dialect_santamarianebaj",
425
+ "Izere (izr)": "izr",
426
+ "Izii (izz)": "izz",
427
+ "Jakalteko (jac)": "jac",
428
+ "Jamaican English Creole (jam)": "jam",
429
+ "Javanese (jav)": "jav",
430
+ "Jukun Takum (jbu)": "jbu",
431
+ "Dza (jen)": "jen",
432
+ "Tol (jic)": "jic",
433
+ "Shuar (jiv)": "jiv",
434
+ "Machame (jmc)": "jmc",
435
+ "Yamdena (jmd)": "jmd",
436
+ "Japanese (jpn)": "jpn",
437
+ "Juang (jun)": "jun",
438
+ "Juray (juy)": "juy",
439
+ "Javanese, Suriname (jvn)": "jvn",
440
+ "Karakalpak (kaa)": "kaa",
441
+ "Amazigh (kab)": "kab",
442
+ "Jingpho (kac)": "kac",
443
+ "Kalanguya (kak)": "kak",
444
+ "Kamba (kam)": "kam",
445
+ "Kannada (kan)": "kan",
446
+ "Xaasongaxango (kao)": "kao",
447
+ "Capanahua (kaq)": "kaq",
448
+ "Georgian (kat)": "kat",
449
+ "Kamayur\u00e1 (kay)": "kay",
450
+ "Kazakh (kaz)": "kaz",
451
+ "Keliko (kbo)": "kbo",
452
+ "Kabiy\u00e8 (kbp)": "kbp",
453
+ "Kamano (kbq)": "kbq",
454
+ "Kafa (kbr)": "kbr",
455
+ "Kanuri, Manga (kby)": "kby",
456
+ "Khanty (kca)": "kca",
457
+ "Tyap (kcg)": "kcg",
458
+ "Kutu (kdc)": "kdc",
459
+ "Makonde (kde)": "kde",
460
+ "Tem (kdh)": "kdh",
461
+ "Kumam (kdi)": "kdi",
462
+ "Ng\u2019akarimojong (kdj)": "kdj",
463
+ "Tsikimba (kdl)": "kdl",
464
+ "Kunda (kdn)": "kdn",
465
+ "Kuay (kdt)": "kdt",
466
+ "Kabuverdianu (kea)": "kea",
467
+ "Q\u2019eqchi\u2019 (kek)": "kek",
468
+ "Kenyang (ken)": "ken",
469
+ "Kakwa (keo)": "keo",
470
+ "Kera (ker)": "ker",
471
+ "Kupia (key)": "key",
472
+ "Kukele (kez)": "kez",
473
+ "Kolami, Northwestern (kfb)": "kfb",
474
+ "Koya (kff-script_telugu)": "kff-script_telugu",
475
+ "Naga, Kharam (kfw)": "kfw",
476
+ "Pahari, Kullu (kfx)": "kfx",
477
+ "Tibetan, Khams (khg)": "khg",
478
+ "Khmer (khm)": "khm",
479
+ "Songhay, Koyra Chiini (khq)": "khq",
480
+ "Kim (kia)": "kia",
481
+ "Kilivila (kij)": "kij",
482
+ "Gikuyu (kik)": "kik",
483
+ "Kinyarwanda (kin)": "kin",
484
+ "Kyrgyz (kir)": "kir",
485
+ "Q\u2019anjob\u2019al (kjb)": "kjb",
486
+ "Kisar (kje)": "kje",
487
+ "Khmu (kjg)": "kjg",
488
+ "Khakas (kjh)": "kjh",
489
+ "Kagulu (kki)": "kki",
490
+ "Kako (kkj)": "kkj",
491
+ "Kulung (kle)": "kle",
492
+ "Klao (klu)": "klu",
493
+ "Maskelynes (klv)": "klv",
494
+ "Tado (klw)": "klw",
495
+ "Konni (kma)": "kma",
496
+ "Kalinga, Majukayang (kmd)": "kmd",
497
+ "Kalinga, Tanudan (kml)": "kml",
498
+ "Kurdish, Northern (kmr-script_arabic)": "kmr-script_arabic",
499
+ "Kurdish, Northern (kmr-script_cyrillic)": "kmr-script_cyrillic",
500
+ "Kurdish, Northern (kmr-script_latin)": "kmr-script_latin",
501
+ "Kanite (kmu)": "kmu",
502
+ "Kalinga, Lubuagan (knb)": "knb",
503
+ "Kankanaey (kne)": "kne",
504
+ "Mankanya (knf)": "knf",
505
+ "Akateko (knj)": "knj",
506
+ "Kuranko (knk)": "knk",
507
+ "Kono (kno)": "kno",
508
+ "Kogi (kog)": "kog",
509
+ "Korean (kor)": "kor",
510
+ "Korupun-Sela (kpq)": "kpq",
511
+ "Tehit (kps)": "kps",
512
+ "Komi-Zyrian (kpv)": "kpv",
513
+ "Koryak (kpy)": "kpy",
514
+ "Kupsapiiny (kpz)": "kpz",
515
+ "Kalagan (kqe)": "kqe",
516
+ "Kimr\u00e9 (kqp)": "kqp",
517
+ "Kimaragang (kqr)": "kqr",
518
+ "Koorete (kqy)": "kqy",
519
+ "Karachay-Balkar (krc)": "krc",
520
+ "Krio (kri)": "kri",
521
+ "Kinaray-a (krj)": "krj",
522
+ "Karelian (krl)": "krl",
523
+ "Krung (krr)": "krr",
524
+ "Gbaya (krs)": "krs",
525
+ "Kurux (kru)": "kru",
526
+ "Shambala (ksb)": "ksb",
527
+ "Borong (ksr)": "ksr",
528
+ "Kisi, Southern (kss)": "kss",
529
+ "Kambaata (ktb)": "ktb",
530
+ "Krumen, Plapo (ktj)": "ktj",
531
+ "Kutep (kub)": "kub",
532
+ "Kuman (kue)": "kue",
533
+ "Kumyk (kum)": "kum",
534
+ "Kusaal (kus)": "kus",
535
+ "Kuna, Border (kvn)": "kvn",
536
+ "Wersing (kvw)": "kvw",
537
+ "Kwaio (kwd)": "kwd",
538
+ "Kwara\u2019ae (kwf)": "kwf",
539
+ "Awa-Cuaiquer (kwi)": "kwi",
540
+ "Konso (kxc)": "kxc",
541
+ "Kawyaw (kxf)": "kxf",
542
+ "Khmer, Northern (kxm)": "kxm",
543
+ "Kuvi (kxv)": "kxv",
544
+ "Kalinga, Butbut (kyb)": "kyb",
545
+ "Kyaka (kyc)": "kyc",
546
+ "Kouya (kyf)": "kyf",
547
+ "Keyagana (kyg)": "kyg",
548
+ "Klon (kyo)": "kyo",
549
+ "Kenga (kyq)": "kyq",
550
+ "Kayah, Western (kyu)": "kyu",
551
+ "Kayab\u00ed (kyz)": "kyz",
552
+ "Kaili, Da\u2019a (kzf)": "kzf",
553
+ "Lacandon (lac)": "lac",
554
+ "Lango (laj)": "laj",
555
+ "Lamba (lam)": "lam",
556
+ "Lao (lao)": "lao",
557
+ "Lama (las)": "las",
558
+ "Latin (lat)": "lat",
559
+ "Latvian (lav)": "lav",
560
+ "Lauje (law)": "law",
561
+ "Ladakhi (lbj)": "lbj",
562
+ "Tolaki (lbw)": "lbw",
563
+ "Lawa, Western (lcp)": "lcp",
564
+ "Ly\u00e9l\u00e9 (lee)": "lee",
565
+ "Lelemi (lef)": "lef",
566
+ "Nomaande (lem)": "lem",
567
+ "Kaili, Ledo (lew)": "lew",
568
+ "Luang (lex)": "lex",
569
+ "Lugbara (lgg)": "lgg",
570
+ "Wala (lgl)": "lgl",
571
+ "Lahu (lhu)": "lhu",
572
+ "Limba, West-Central (lia)": "lia",
573
+ "Nyindrou (lid)": "lid",
574
+ "Limbu (lif)": "lif",
575
+ "Lingala (lin)": "lin",
576
+ "Sekpele (lip)": "lip",
577
+ "Lisu (lis)": "lis",
578
+ "Lithuanian (lit)": "lit",
579
+ "Rampi (lje)": "lje",
580
+ "Lampung Api (ljp)": "ljp",
581
+ "Lole (llg)": "llg",
582
+ "Lele (lln)": "lln",
583
+ "P\u00e9v\u00e9 (lme)": "lme",
584
+ "Lundayeh (lnd)": "lnd",
585
+ "Lamnso\u2019 (lns)": "lns",
586
+ "Lobi (lob)": "lob",
587
+ "Loko (lok)": "lok",
588
+ "Loma (lom)": "lom",
589
+ "Lomwe, Malawi (lon)": "lon",
590
+ "Lobala (loq)": "loq",
591
+ "Lacid (lsi)": "lsi",
592
+ "Saamya-Gwe (lsm)": "lsm",
593
+ "Luxembourgish (ltz)": "ltz",
594
+ "Aringa (luc)": "luc",
595
+ "Ganda (lug)": "lug",
596
+ "Dholuo (luo)": "luo",
597
+ "Luwo (lwo)": "lwo",
598
+ "Lewo (lww)": "lww",
599
+ "Laz (lzz)": "lzz",
600
+ "Mazatec, San Jer\u00f3nimo Tec\u00f3atl (maa-dialect_sanantonio)": "maa-dialect_sanantonio",
601
+ "Mazatec, San Jer\u00f3nimo Tec\u00f3atl (maa-dialect_sanjeronimo)": "maa-dialect_sanjeronimo",
602
+ "Madura (mad)": "mad",
603
+ "Magahi (mag)": "mag",
604
+ "Marshallese (mah)": "mah",
605
+ "Maithili (mai)": "mai",
606
+ "Mazatec, Jalapa de D\u00edaz (maj)": "maj",
607
+ "Makasar (mak)": "mak",
608
+ "Malayalam (mal)": "mal",
609
+ "Mam (mam-dialect_central)": "mam-dialect_central",
610
+ "Mam (mam-dialect_northern)": "mam-dialect_northern",
611
+ "Mam (mam-dialect_southern)": "mam-dialect_southern",
612
+ "Mam (mam-dialect_western)": "mam-dialect_western",
613
+ "Mazatec, Chiquihuitl\u00e1n (maq)": "maq",
614
+ "Marathi (mar)": "mar",
615
+ "Mampruli (maw)": "maw",
616
+ "Mazahua, Central (maz)": "maz",
617
+ "Manobo, Western Bukidnon (mbb)": "mbb",
618
+ "Macushi (mbc)": "mbc",
619
+ "Mangseng (mbh)": "mbh",
620
+ "Nad\u00ebb (mbj)": "mbj",
621
+ "Manobo, Matigsalug (mbt)": "mbt",
622
+ "Mbula-Bwazza (mbu)": "mbu",
623
+ "Mixtec, Amoltepec (mbz)": "mbz",
624
+ "Maka (mca)": "mca",
625
+ "Matsigenka (mcb)": "mcb",
626
+ "Sharanahua (mcd)": "mcd",
627
+ "Mixe, Coatl\u00e1n (mco)": "mco",
628
+ "Makaa (mcp)": "mcp",
629
+ "Ese (mcq)": "mcq",
630
+ "Mambila, Cameroon (mcu)": "mcu",
631
+ "Mada (mda)": "mda",
632
+ "Moksha (mdf)": "mdf",
633
+ "Mixtec, Santa Luc\u00eda Monteverde (mdv)": "mdv",
634
+ "Male (mdy)": "mdy",
635
+ "Melpa (med)": "med",
636
+ "Mengen (mee)": "mee",
637
+ "Meyah (mej)": "mej",
638
+ "Mende (men)": "men",
639
+ "Merey (meq)": "meq",
640
+ "Mato (met)": "met",
641
+ "Maan (mev)": "mev",
642
+ "Morisyen (mfe)": "mfe",
643
+ "Matal (mfh)": "mfh",
644
+ "Wandala (mfi)": "mfi",
645
+ "Mofu, North (mfk)": "mfk",
646
+ "Moba (mfq)": "mfq",
647
+ "Mayo (mfy)": "mfy",
648
+ "Mabaan (mfz)": "mfz",
649
+ "Moru (mgd)": "mgd",
650
+ "Mango (mge)": "mge",
651
+ "Makhuwa-Meetto (mgh)": "mgh",
652
+ "Meta\u2019 (mgo)": "mgo",
653
+ "Ma\u2019di (mhi)": "mhi",
654
+ "Mari, Meadow (mhr)": "mhr",
655
+ "Digaro-Mishmi (mhu)": "mhu",
656
+ "Lhao Vo (mhx)": "mhx",
657
+ "Ma\u2019anyan (mhy)": "mhy",
658
+ "Mixtec, Atatlahuca (mib)": "mib",
659
+ "Mixtec, Ocotepec (mie)": "mie",
660
+ "Mofu-Gudur (mif)": "mif",
661
+ "Mixtec, Chayuco (mih)": "mih",
662
+ "Mixtec, Pe\u00f1oles (mil)": "mil",
663
+ "Mixtec, Alacatlatzala (mim)": "mim",
664
+ "Minangkabau (min)": "min",
665
+ "Mixtec, Pinotepa Nacional (mio)": "mio",
666
+ "Mixtec, Apasco-Apoala (mip)": "mip",
667
+ "M\u00edskito (miq)": "miq",
668
+ "Mixtec, Southern Puebla (mit)": "mit",
669
+ "Mixtec, Ayutla (miy)": "miy",
670
+ "Mixtec, Coatzospan (miz)": "miz",
671
+ "Mandeali (mjl)": "mjl",
672
+ "Mannan (mjv)": "mjv",
673
+ "Macedonian (mkd)": "mkd",
674
+ "Mokole (mkl)": "mkl",
675
+ "Malay, Kupang (mkn)": "mkn",
676
+ "Malagasy (mlg)": "mlg",
677
+ "Maltese (mlt)": "mlt",
678
+ "Ambrym, North (mmg)": "mmg",
679
+ "Muna (mnb)": "mnb",
680
+ "Mundani (mnf)": "mnf",
681
+ "Mandinka (mnk)": "mnk",
682
+ "Mon (mnw)": "mnw",
683
+ "Sougb (mnx)": "mnx",
684
+ "Mwan (moa)": "moa",
685
+ "Mongondow (mog)": "mog",
686
+ "Mongolian (mon)": "mon",
687
+ "Maya, Mop\u00e1n (mop)": "mop",
688
+ "Moro (mor)": "mor",
689
+ "M\u00f2or\u00e9 (mos)": "mos",
690
+ "Molima (mox)": "mox",
691
+ "Mukulu (moz)": "moz",
692
+ "Marba (mpg)": "mpg",
693
+ "Mixtec, Yosond\u00faa (mpm)": "mpm",
694
+ "Migabac (mpp)": "mpp",
695
+ "Misima-Panaeati (mpx)": "mpx",
696
+ "Mbuko (mqb)": "mqb",
697
+ "Momuna (mqf)": "mqf",
698
+ "Mamasa (mqj)": "mqj",
699
+ "Moronene (mqn)": "mqn",
700
+ "Maori (mri)": "mri",
701
+ "Maranao (mrw)": "mrw",
702
+ "Aruamu (msy)": "msy",
703
+ "Mualang (mtd)": "mtd",
704
+ "Moskona (mtj)": "mtj",
705
+ "Mixe, Totontepec (mto)": "mto",
706
+ "M\u00fcnd\u00fc (muh)": "muh",
707
+ "Malvi (mup)": "mup",
708
+ "Murle (mur)": "mur",
709
+ "Muthuvan (muv)": "muv",
710
+ "Muyang (muy)": "muy",
711
+ "Duri (mvp)": "mvp",
712
+ "Chin, M\u00fc\u00fcn (mwq)": "mwq",
713
+ "Mentawai (mwv)": "mwv",
714
+ "Mixtec, Tezoatl\u00e1n (mxb)": "mxb",
715
+ "Mixe, Juquila (mxq)": "mxq",
716
+ "Mixtec, Jamiltepec (mxt)": "mxt",
717
+ "Mixtec, Metlat\u00f3noc (mxv)": "mxv",
718
+ "Burmese (mya)": "mya",
719
+ "Mbay (myb)": "myb",
720
+ "S\u00e9noufo, Mamara (myk)": "myk",
721
+ "Moma (myl)": "myl",
722
+ "Erzya (myv)": "myv",
723
+ "Masaaba (myx)": "myx",
724
+ "Macuna (myy)": "myy",
725
+ "Mixtec, Santa Mar\u00eda Zacatepec (mza)": "mza",
726
+ "Mazatec, Ixcatl\u00e1n (mzi)": "mzi",
727
+ "Manya (mzj)": "mzj",
728
+ "Mambila, Nigeria (mzk)": "mzk",
729
+ "Mumuye (mzm)": "mzm",
730
+ "Deg (mzw)": "mzw",
731
+ "Nambiku\u00e1ra, Southern (nab)": "nab",
732
+ "Nagamese (nag)": "nag",
733
+ "Chinese, Min Nan (nan)": "nan",
734
+ "Naasioi (nas)": "nas",
735
+ "Nawuri (naw)": "naw",
736
+ "Iyo (nca)": "nca",
737
+ "Nahuatl, Central Huasteca (nch)": "nch",
738
+ "Nahuatl, Northern Puebla (ncj)": "ncj",
739
+ "Nahuatl, Michoac\u00e1n (ncl)": "ncl",
740
+ "Chumburung (ncu)": "ncu",
741
+ "Ndamba (ndj)": "ndj",
742
+ "Kebu (ndp)": "ndp",
743
+ "Ndut (ndv)": "ndv",
744
+ "Lutos (ndy)": "ndy",
745
+ "Ndogo (ndz)": "ndz",
746
+ "Toura (neb)": "neb",
747
+ "Newar (new)": "new",
748
+ "Dhao (nfa)": "nfa",
749
+ "Nafaanra (nfr)": "nfr",
750
+ "Ngbaka (nga)": "nga",
751
+ "Lomwe (ngl)": "ngl",
752
+ "Ngulu (ngp)": "ngp",
753
+ "Nahuatl, Guerrero (ngu)": "ngu",
754
+ "Nahuatl, Eastern Huasteca (nhe)": "nhe",
755
+ "Nahuatl, Zacatl\u00e1n-Ahuacatl\u00e1n-Tepetzintla (nhi)": "nhi",
756
+ "Noone (nhu)": "nhu",
757
+ "Nahuatl, Western Huasteca (nhw)": "nhw",
758
+ "Nahuatl, Isthmus-Mecayapan (nhx)": "nhx",
759
+ "Nahuatl, Northern Oaxaca (nhy)": "nhy",
760
+ "Nias (nia)": "nia",
761
+ "Ngaju (nij)": "nij",
762
+ "Nilamba (nim)": "nim",
763
+ "Ninzo (nin)": "nin",
764
+ "Nkonya (nko)": "nko",
765
+ "Nalca (nlc)": "nlc",
766
+ "Dutch (nld)": "nld",
767
+ "Gela (nlg)": "nlg",
768
+ "Yali, Ninia (nlk)": "nlk",
769
+ "Nawdm (nmz)": "nmz",
770
+ "Nande (nnb)": "nnb",
771
+ "Norwegian Nynorsk (nno)": "nno",
772
+ "Ngindo (nnq)": "nnq",
773
+ "Nuni, Southern (nnw)": "nnw",
774
+ "Woun Meu (noa)": "noa",
775
+ "Norwegian Bokm\u00e5l (nob)": "nob",
776
+ "Thai, Northern (nod)": "nod",
777
+ "Nogai (nog)": "nog",
778
+ "Nomatsigenga (not)": "not",
779
+ "Nepali (npi)": "npi",
780
+ "Nahuatl, Southeastern Puebla (npl)": "npl",
781
+ "Napu (npy)": "npy",
782
+ "Sotho, Northern (nso)": "nso",
783
+ "Naga, Tangshang (nst)": "nst",
784
+ "Nahuatl, Sierra Negra (nsu)": "nsu",
785
+ "Nateni (ntm)": "ntm",
786
+ "Delo (ntr)": "ntr",
787
+ "Nyole (nuj)": "nuj",
788
+ "Nuer (nus)": "nus",
789
+ "Nahuatl, Tlamacazapa (nuz)": "nuz",
790
+ "Nyabwa (nwb)": "nwb",
791
+ "Naxi (nxq)": "nxq",
792
+ "Chichewa (nya)": "nya",
793
+ "Kigiryama (nyf)": "nyf",
794
+ "Nyankore (nyn)": "nyn",
795
+ "Nyoro (nyo)": "nyo",
796
+ "Nyakyusa-Ngonde (nyy)": "nyy",
797
+ "Nzema (nzi)": "nzi",
798
+ "Manobo, Obo (obo)": "obo",
799
+ "Occitan (oci)": "oci",
800
+ "Ojibwa, Northwestern (ojb-script_latin)": "ojb-script_latin",
801
+ "Ojibwa, Northwestern (ojb-script_syllabics)": "ojb-script_syllabics",
802
+ "Oku (oku)": "oku",
803
+ "Mochi (old)": "old",
804
+ "Tairora, South (omw)": "omw",
805
+ "Lingao (onb)": "onb",
806
+ "Tohono O\u2019odham (ood)": "ood",
807
+ "Oromo (orm)": "orm",
808
+ "Odia (ory)": "ory",
809
+ "Ossetic (oss)": "oss",
810
+ "Otomi, Mezquital (ote)": "ote",
811
+ "Otomi, Quer\u00e9taro (otq)": "otq",
812
+ "Koonzime (ozm)": "ozm",
813
+ "Parec\u00eds (pab)": "pab",
814
+ "Paumar\u00ed (pad)": "pad",
815
+ "Pangasinan (pag)": "pag",
816
+ "Kapampangan (pam)": "pam",
817
+ "Punjabi, Eastern (pan)": "pan",
818
+ "Paiute, Northern (pao)": "pao",
819
+ "Papiamentu (pap)": "pap",
820
+ "Palauan (pau)": "pau",
821
+ "Nasa (pbb)": "pbb",
822
+ "Patamona (pbc)": "pbc",
823
+ "Parkwa (pbi)": "pbi",
824
+ "Palaung, Ruching (pce)": "pce",
825
+ "Pidgin, Nigerian (pcm)": "pcm",
826
+ "Pengo (peg)": "peg",
827
+ "Penan, Eastern (pez)": "pez",
828
+ "Yine (pib)": "pib",
829
+ "Yom (pil)": "pil",
830
+ "Piratapuyo (pir)": "pir",
831
+ "Pijin (pis)": "pis",
832
+ "Pitjantjatjara (pjt)": "pjt",
833
+ "Kipfokomo (pkb)": "pkb",
834
+ "Popoloca, San Marcos Tlacoyalco (pls)": "pls",
835
+ "Palawano, Brooke\u2019s Point (plw)": "plw",
836
+ "Pamona (pmf)": "pmf",
837
+ "Pinyin (pny)": "pny",
838
+ "Poqomchi\u2019 (poh-dialect_eastern)": "poh-dialect_eastern",
839
+ "Poqomchi\u2019 (poh-dialect_western)": "poh-dialect_western",
840
+ "Popoluca, Highland (poi)": "poi",
841
+ "Polish (pol)": "pol",
842
+ "Portuguese (por)": "por",
843
+ "Pogolo (poy)": "poy",
844
+ "Uma (ppk)": "ppk",
845
+ "Popoloca, San Lu\u00eds Temalacayuca (pps)": "pps",
846
+ "Paranan (prf)": "prf",
847
+ "Wa, Parauk (prk)": "prk",
848
+ "Prai (prt)": "prt",
849
+ "Malay, Central (pse)": "pse",
850
+ "Kaulong (pss)": "pss",
851
+ "Bambam (ptu)": "ptu",
852
+ "Puinave (pui)": "pui",
853
+ "Pushto (pus)": "pus",
854
+ "Gapapaiwa (pwg)": "pwg",
855
+ "Karen, Pwo Northern (pww)": "pww",
856
+ "Mixe, Quetzaltepec (pxm)": "pxm",
857
+ "Quechua, Huallaga (qub)": "qub",
858
+ "K\u2019iche\u2019 (quc-dialect_central)": "quc-dialect_central",
859
+ "K\u2019iche\u2019 (quc-dialect_east)": "quc-dialect_east",
860
+ "K\u2019iche\u2019 (quc-dialect_north)": "quc-dialect_north",
861
+ "Quechua, Lambayeque (quf)": "quf",
862
+ "Quechua, South Bolivian (quh)": "quh",
863
+ "Quechua, North Bolivian (qul)": "qul",
864
+ "Quichua, Tena Lowland (quw)": "quw",
865
+ "Quechua, Ayacucho (quy)": "quy",
866
+ "Quechua, Cusco (quz)": "quz",
867
+ "Quechua, Cajamarca (qvc)": "qvc",
868
+ "Quechua, Eastern Apur\u00edmac (qve)": "qve",
869
+ "Quechua, Huamal\u00edes-Dos de Mayo Hu\u00e1nuco (qvh)": "qvh",
870
+ "Quechua, Margos-Yarowilca-Lauricocha (qvm)": "qvm",
871
+ "Quechua, North Jun\u00edn (qvn)": "qvn",
872
+ "Quichua, Napo (qvo)": "qvo",
873
+ "Quechua, San Mart\u00edn (qvs)": "qvs",
874
+ "Quechua, Huaylla Wanca (qvw)": "qvw",
875
+ "Quichua, Northern Pastaza (qvz)": "qvz",
876
+ "Quechua, Huaylas Ancash (qwh)": "qwh",
877
+ "Quechua, Panao (qxh)": "qxh",
878
+ "Quichua, Salasaca Highland (qxl)": "qxl",
879
+ "Quechua, Northern Conchucos Ancash (qxn)": "qxn",
880
+ "Quechua, Southern Conchucos (qxo)": "qxo",
881
+ "Quichua, Ca\u00f1ar Highland (qxr)": "qxr",
882
+ "Rabha (rah)": "rah",
883
+ "Ramoaaina (rai)": "rai",
884
+ "Rapa Nui (rap)": "rap",
885
+ "Sampang (rav)": "rav",
886
+ "Rawang (raw)": "raw",
887
+ "Rejang (rej)": "rej",
888
+ "Rendille (rel)": "rel",
889
+ "Rikou (rgu)": "rgu",
890
+ "Rohingya (rhg)": "rhg",
891
+ "Tarifit (rif-script_arabic)": "rif-script_arabic",
892
+ "Tarifit (rif-script_latin)": "rif-script_latin",
893
+ "Riang Lang (ril)": "ril",
894
+ "Nyaturu (rim)": "rim",
895
+ "Rajbanshi (rjs)": "rjs",
896
+ "Rangpuri (rkt)": "rkt",
897
+ "Romani, Carpathian (rmc-script_cyrillic)": "rmc-script_cyrillic",
898
+ "Romani, Carpathian (rmc-script_latin)": "rmc-script_latin",
899
+ "Romani, Sinte (rmo)": "rmo",
900
+ "Romani, Vlax (rmy-script_cyrillic)": "rmy-script_cyrillic",
901
+ "Romani, Vlax (rmy-script_latin)": "rmy-script_latin",
902
+ "Ronga (rng)": "rng",
903
+ "Ranglong (rnl)": "rnl",
904
+ "Romansh (roh-dialect_sursilv)": "roh-dialect_sursilv",
905
+ "Romansh (roh-dialect_vallader)": "roh-dialect_vallader",
906
+ "Romblomanon (rol)": "rol",
907
+ "Romanian (ron)": "ron",
908
+ "Kriol (rop)": "rop",
909
+ "Waima (rro)": "rro",
910
+ "Gungu (rub)": "rub",
911
+ "Luguru (ruf)": "ruf",
912
+ "Roviana (rug)": "rug",
913
+ "Rundi (run)": "run",
914
+ "Russian (rus)": "rus",
915
+ "Buglere (sab)": "sab",
916
+ "Sango (sag)": "sag",
917
+ "Yakut (sah)": "sah",
918
+ "Sahu (saj)": "saj",
919
+ "Samburu (saq)": "saq",
920
+ "Sasak (sas)": "sas",
921
+ "Santhali (sat)": "sat",
922
+ "Ngambay (sba)": "sba",
923
+ "Samo, Southern (sbd)": "sbd",
924
+ "Sambal, Botolan (sbl)": "sbl",
925
+ "Sangu (sbp)": "sbp",
926
+ "Sakachep (sch)": "sch",
927
+ "Sadri (sck)": "sck",
928
+ "Toraja-Sa\u2019dan (sda)": "sda",
929
+ "Semai (sea)": "sea",
930
+ "Sena (seh)": "seh",
931
+ "Songhay, Koyraboro Senni (ses)": "ses",
932
+ "Paicoca (sey)": "sey",
933
+ "Ayta, Mag-antsi (sgb)": "sgb",
934
+ "Surgujia (sgj)": "sgj",
935
+ "Sebat Bet Gurage (sgw)": "sgw",
936
+ "Tachelhit (shi)": "shi",
937
+ "Shilluk (shk)": "shk",
938
+ "Shan (shn)": "shn",
939
+ "Shanga (sho)": "sho",
940
+ "Shipibo-Conibo (shp)": "shp",
941
+ "Sidamo (sid)": "sid",
942
+ "Paasaal (sig)": "sig",
943
+ "Sisaala, Tumulung (sil)": "sil",
944
+ "Epena (sja)": "sja",
945
+ "Mapun (sjm)": "sjm",
946
+ "Sissala (sld)": "sld",
947
+ "Slovak (slk)": "slk",
948
+ "Selaru (slu)": "slu",
949
+ "Slovene (slv)": "slv",
950
+ "Sama, Central (sml)": "sml",
951
+ "Samoan (smo)": "smo",
952
+ "Shona (sna)": "sna",
953
+ "Sindhi (snd)": "snd",
954
+ "Bidayuh, Bau (sne)": "sne",
955
+ "Siona (snn)": "snn",
956
+ "Siane (snp)": "snp",
957
+ "Selee (snw)": "snw",
958
+ "Somali (som)": "som",
959
+ "Miyobe (soy)": "soy",
960
+ "Spanish (spa)": "spa",
961
+ "S\u00e9noufo, Supyire (spp)": "spp",
962
+ "Sabaot (spy)": "spy",
963
+ "Albanian (sqi)": "sqi",
964
+ "Siriano (sri)": "sri",
965
+ "Saramaccan (srm)": "srm",
966
+ "Sranan Tongo (srn)": "srn",
967
+ "Serbian (srp-script_cyrillic)": "srp-script_cyrillic",
968
+ "Serbian (srp-script_latin)": "srp-script_latin",
969
+ "Sirmauri (srx)": "srx",
970
+ "Owa (stn)": "stn",
971
+ "Tepehuan, Southeastern (stp)": "stp",
972
+ "Subanon, Western (suc)": "suc",
973
+ "Sukuma (suk)": "suk",
974
+ "Sunda (sun)": "sun",
975
+ "Mwaghavul (sur)": "sur",
976
+ "Susu (sus)": "sus",
977
+ "Puroik (suv)": "suv",
978
+ "Sunwar (suz)": "suz",
979
+ "Swedish (swe)": "swe",
980
+ "Swahili (swh)": "swh",
981
+ "Suba (sxb)": "sxb",
982
+ "Sangir (sxn)": "sxn",
983
+ "Siang (sya)": "sya",
984
+ "Sylheti (syl)": "syl",
985
+ "Semelai (sza)": "sza",
986
+ "Tarahumara, Western (tac)": "tac",
987
+ "Tamang, Eastern (taj)": "taj",
988
+ "Tamil (tam)": "tam",
989
+ "Yami (tao)": "tao",
990
+ "Taabwa (tap)": "tap",
991
+ "Tamasheq (taq)": "taq",
992
+ "Tatar (tat)": "tat",
993
+ "Tatuyo (tav)": "tav",
994
+ "Takia (tbc)": "tbc",
995
+ "Tairora, North (tbg)": "tbg",
996
+ "Tagbanwa, Calamian (tbk)": "tbk",
997
+ "Tboli (tbl)": "tbl",
998
+ "Tabaru (tby)": "tby",
999
+ "Ditammari (tbz)": "tbz",
1000
+ "Ticuna (tca)": "tca",
1001
+ "Datooga (tcc)": "tcc",
1002
+ "Torres Strait Creole (tcs)": "tcs",
1003
+ "Chin, Thado (tcz)": "tcz",
1004
+ "Tajio (tdj)": "tdj",
1005
+ "Krumen, Tepo (ted)": "ted",
1006
+ "Tepehua, Huehuetla (tee)": "tee",
1007
+ "Telugu (tel)": "tel",
1008
+ "Themne (tem)": "tem",
1009
+ "Ateso (teo)": "teo",
1010
+ "Ter\u00eana (ter)": "ter",
1011
+ "Tengger (tes)": "tes",
1012
+ "Tewa (tew)": "tew",
1013
+ "Tennet (tex)": "tex",
1014
+ "Teribe (tfr)": "tfr",
1015
+ "Tagin (tgj)": "tgj",
1016
+ "Tajik (tgk)": "tgk",
1017
+ "Tagalog (tgl)": "tgl",
1018
+ "Sudest (tgo)": "tgo",
1019
+ "Tangoa (tgp)": "tgp",
1020
+ "Thai (tha)": "tha",
1021
+ "Kitharaka (thk)": "thk",
1022
+ "Tharu, Dangaura (thl)": "thl",
1023
+ "Murut, Timugon (tih)": "tih",
1024
+ "Tikar (tik)": "tik",
1025
+ "Tigrigna (tir)": "tir",
1026
+ "Tsakhur (tkr)": "tkr",
1027
+ "Tobelo (tlb)": "tlb",
1028
+ "Talinga-Bwisi (tlj)": "tlj",
1029
+ "Talysh (tly)": "tly",
1030
+ "Tumak (tmc)": "tmc",
1031
+ "Toba-Maskoy (tmf)": "tmf",
1032
+ "Tacana (tna)": "tna",
1033
+ "Tobanga (tng)": "tng",
1034
+ "Kwamera (tnk)": "tnk",
1035
+ "Tanna, North (tnn)": "tnn",
1036
+ "Whitesands (tnp)": "tnp",
1037
+ "M\u00e9nik (tnr)": "tnr",
1038
+ "Tontemboan (tnt)": "tnt",
1039
+ "Toba (tob)": "tob",
1040
+ "Totonac, Coyutla (toc)": "toc",
1041
+ "Tonga (toh)": "toh",
1042
+ "Tombulu (tom)": "tom",
1043
+ "Totonac, Highland (tos)": "tos",
1044
+ "Tok Pisin (tpi)": "tpi",
1045
+ "Tampulma (tpm)": "tpm",
1046
+ "Tepehua, Pisaflores (tpp)": "tpp",
1047
+ "Tepehua, Tlachichilco (tpt)": "tpt",
1048
+ "Triqui, Copala (trc)": "trc",
1049
+ "Tri\u00f3 (tri)": "tri",
1050
+ "Trinitario (trn)": "trn",
1051
+ "Triqui, Chicahuaxtla (trs)": "trs",
1052
+ "Tsonga (tso)": "tso",
1053
+ "Purepecha (tsz)": "tsz",
1054
+ "Tektiteko (ttc)": "ttc",
1055
+ "Bwanabwana (tte)": "tte",
1056
+ "Tamajaq, Tawallammat (ttq-script_tifinagh)": "ttq-script_tifinagh",
1057
+ "Tuyuca (tue)": "tue",
1058
+ "Tunebo, Central (tuf)": "tuf",
1059
+ "Turkmen (tuk-script_arabic)": "tuk-script_arabic",
1060
+ "Turkmen (tuk-script_latin)": "tuk-script_latin",
1061
+ "Tucano (tuo)": "tuo",
1062
+ "Turkish (tur)": "tur",
1063
+ "Sedoa (tvw)": "tvw",
1064
+ "Tawbuid (twb)": "twb",
1065
+ "Teiwa (twe)": "twe",
1066
+ "Termanu (twu)": "twu",
1067
+ "Tombonuo (txa)": "txa",
1068
+ "Tii (txq)": "txq",
1069
+ "Kayap\u00f3 (txu)": "txu",
1070
+ "Kyanga (tye)": "tye",
1071
+ "Tzeltal (tzh-dialect_bachajon)": "tzh-dialect_bachajon",
1072
+ "Tzeltal (tzh-dialect_tenejapa)": "tzh-dialect_tenejapa",
1073
+ "Tz\u2019utujil (tzj-dialect_eastern)": "tzj-dialect_eastern",
1074
+ "Tz\u2019utujil (tzj-dialect_western)": "tzj-dialect_western",
1075
+ "Tzotzil (tzo-dialect_chamula)": "tzo-dialect_chamula",
1076
+ "Tzotzil (tzo-dialect_chenalho)": "tzo-dialect_chenalho",
1077
+ "Bikol, Buhi\u2019non (ubl)": "ubl",
1078
+ "Umbu-Ungu (ubu)": "ubu",
1079
+ "Udmurt (udm)": "udm",
1080
+ "Uduk (udu)": "udu",
1081
+ "Uyghur (uig-script_arabic)": "uig-script_arabic",
1082
+ "Uyghur (uig-script_cyrillic)": "uig-script_cyrillic",
1083
+ "Ukrainian (ukr)": "ukr",
1084
+ "Umbundu (umb)": "umb",
1085
+ "Mundari (unr)": "unr",
1086
+ "Uripiv-Wala-Rano-Atchin (upv)": "upv",
1087
+ "Urarina (ura)": "ura",
1088
+ "Kaapor (urb)": "urb",
1089
+ "Urdu (urd-script_arabic)": "urd-script_arabic",
1090
+ "Urdu (urd-script_devanagari)": "urd-script_devanagari",
1091
+ "Urdu (urd-script_latin)": "urd-script_latin",
1092
+ "Urak Lawoi\u2019 (urk)": "urk",
1093
+ "Urat (urt)": "urt",
1094
+ "Orya (ury)": "ury",
1095
+ "Uspanteko (usp)": "usp",
1096
+ "Uzbek (uzb-script_cyrillic)": "uzb-script_cyrillic",
1097
+ "Uzbek (uzb-script_latin)": "uzb-script_latin",
1098
+ "Vagla (vag)": "vag",
1099
+ "Vidunda (vid)": "vid",
1100
+ "Vietnamese (vie)": "vie",
1101
+ "Vili (vif)": "vif",
1102
+ "Makhuwa (vmw)": "vmw",
1103
+ "Mazatec, Ayautla (vmy)": "vmy",
1104
+ "Vod (vot)": "vot",
1105
+ "Vunjo (vun)": "vun",
1106
+ "Vute (vut)": "vut",
1107
+ "Wolaytta (wal-script_ethiopic)": "wal-script_ethiopic",
1108
+ "Wolaytta (wal-script_latin)": "wal-script_latin",
1109
+ "Wapishana (wap)": "wap",
1110
+ "Waray-Waray (war)": "war",
1111
+ "Waiwai (waw)": "waw",
1112
+ "Wayana (way)": "way",
1113
+ "Warao (wba)": "wba",
1114
+ "Wolio (wlo)": "wlo",
1115
+ "Wali (wlx)": "wlx",
1116
+ "Mwani (wmw)": "wmw",
1117
+ "W\u00e8 Northern (wob)": "wob",
1118
+ "Wolof (wol)": "wol",
1119
+ "Gondi, Adilabad (wsg)": "wsg",
1120
+ "Waama (wwa)": "wwa",
1121
+ "Kalmyk-Oirat (xal)": "xal",
1122
+ "Malayic Dayak (xdy)": "xdy",
1123
+ "Hdi (xed)": "xed",
1124
+ "Xer\u00e9nte (xer)": "xer",
1125
+ "Xhosa (xho)": "xho",
1126
+ "Malay, Manado (xmm)": "xmm",
1127
+ "Chingoni (xnj)": "xnj",
1128
+ "Kangri (xnr)": "xnr",
1129
+ "Soga (xog)": "xog",
1130
+ "Konkomba (xon)": "xon",
1131
+ "Karaboro, Eastern (xrb)": "xrb",
1132
+ "Sambal (xsb)": "xsb",
1133
+ "Kasem (xsm)": "xsm",
1134
+ "Sherpa (xsr)": "xsr",
1135
+ "Sanum\u00e1 (xsu)": "xsu",
1136
+ "Mixtec, Alcozauca (xta)": "xta",
1137
+ "Mixtec, Diuxi-Tilantongo (xtd)": "xtd",
1138
+ "Ketengban (xte)": "xte",
1139
+ "Mixtec, Magdalena Pe\u00f1asco (xtm)": "xtm",
1140
+ "Mixtec, Northern Tlaxiaco (xtn)": "xtn",
1141
+ "Kurumba, Alu (xua)": "xua",
1142
+ "Kuo (xuo)": "xuo",
1143
+ "Yaminahua (yaa)": "yaa",
1144
+ "Yagua (yad)": "yad",
1145
+ "Yalunka (yal)": "yal",
1146
+ "Yamba (yam)": "yam",
1147
+ "Yao (yao)": "yao",
1148
+ "Nugunu (yas)": "yas",
1149
+ "Yambeta (yat)": "yat",
1150
+ "Lokaa (yaz)": "yaz",
1151
+ "Yala (yba)": "yba",
1152
+ "Yemba (ybb)": "ybb",
1153
+ "Lolopo (ycl)": "ycl",
1154
+ "Yucuna (ycn)": "ycn",
1155
+ "Ravula (yea)": "yea",
1156
+ "Yakan (yka)": "yka",
1157
+ "Yali, Angguruk (yli)": "yli",
1158
+ "Yoruba (yor)": "yor",
1159
+ "Yaour\u00e9 (yre)": "yre",
1160
+ "Maya, Yucatec (yua)": "yua",
1161
+ "Chinese, Yue (yue-script_traditional)": "yue-script_traditional",
1162
+ "Yuracare (yuz)": "yuz",
1163
+ "Yawa (yva)": "yva",
1164
+ "Zapotec, Sierra de Ju\u00e1rez (zaa)": "zaa",
1165
+ "Zapotec, Western Tlacolula Valley (zab)": "zab",
1166
+ "Zapotec, Ocotl\u00e1n (zac)": "zac",
1167
+ "Zapotec, Cajonos (zad)": "zad",
1168
+ "Zapotec, Yareni (zae)": "zae",
1169
+ "Zapotec, Isthmus (zai)": "zai",
1170
+ "Zapotec, Miahuatl\u00e1n (zam)": "zam",
1171
+ "Zapotec, Ozolotepec (zao)": "zao",
1172
+ "Zapotec, Alo\u00e1pam (zaq)": "zaq",
1173
+ "Zapotec, Rinc\u00f3n (zar)": "zar",
1174
+ "Zapotec, Santo Domingo Albarradas (zas)": "zas",
1175
+ "Zapotec, Yatzachi (zav)": "zav",
1176
+ "Zapotec, Mitla (zaw)": "zaw",
1177
+ "Zapotec, Coatecas Altas (zca)": "zca",
1178
+ "Kinga (zga)": "zga",
1179
+ "Mesme (zim)": "zim",
1180
+ "Zigula (ziw)": "ziw",
1181
+ "Malay (zlm)": "zlm",
1182
+ "Mbandja (zmz)": "zmz",
1183
+ "Zande (zne)": "zne",
1184
+ "Zoque, Francisco Le\u00f3n (zos)": "zos",
1185
+ "Zapotec, Choapan (zpc)": "zpc",
1186
+ "Zapotec, Guevea de Humboldt (zpg)": "zpg",
1187
+ "Zapotec, Santa Mar\u00eda Quiegolani (zpi)": "zpi",
1188
+ "Zapotec, Lachix\u00edo (zpl)": "zpl",
1189
+ "Zapotec, Mixtepec (zpm)": "zpm",
1190
+ "Zapotec, Amatl\u00e1n (zpo)": "zpo",
1191
+ "Zapotec, San Vicente Coatl\u00e1n (zpt)": "zpt",
1192
+ "Zapotec, Yal\u00e1lag (zpu)": "zpu",
1193
+ "Zapotec, Texmelucan (zpz)": "zpz",
1194
+ "Zapotec, Quioquitani-Quier\u00ed (ztq)": "ztq",
1195
+ "Zapotec, Yatee (zty)": "zty",
1196
+ "Zulu (zul)": "zul",
1197
+ "Zhuang, Yongbei (zyb)": "zyb",
1198
+ "Chin, Zyphe (zyp)": "zyp",
1199
+ "Zaza (zza)": "zza"
1200
+ }
README.md CHANGED
@@ -6,7 +6,7 @@ colorTo: pink
6
  sdk: gradio
7
  sdk_version: 3.33.1
8
  app_file: app.py
9
- pinned: false
10
  ---
11
 
12
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
6
  sdk: gradio
7
  sdk_version: 3.33.1
8
  app_file: app.py
9
+ pinned: true
10
  ---
11
 
12
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
app.py CHANGED
@@ -2,12 +2,18 @@ import gradio as gr
2
  from transformers import Wav2Vec2ForCTC, AutoProcessor
3
  import torch
4
  import librosa
 
 
 
 
 
 
5
 
6
  model_id = "facebook/mms-1b-all"
7
  processor = AutoProcessor.from_pretrained(model_id)
8
  model = Wav2Vec2ForCTC.from_pretrained(model_id)
9
 
10
- def transcribe(audio_file_mic=None, audio_file_upload=None, language="eng"):
11
  if audio_file_mic:
12
  audio_file = audio_file_mic
13
  elif audio_file_upload:
@@ -21,8 +27,9 @@ def transcribe(audio_file_mic=None, audio_file_upload=None, language="eng"):
21
  speech = librosa.resample(speech, orig_sr=sample_rate, target_sr=16000)
22
 
23
  # Keep the same model in memory and simply switch out the language adapters by calling load_adapter() for the model and set_target_lang() for the tokenizer
24
- processor.tokenizer.set_target_lang(language)
25
- model.load_adapter(language)
 
26
 
27
  inputs = processor(speech, sampling_rate=16_000, return_tensors="pt")
28
 
@@ -33,10 +40,8 @@ def transcribe(audio_file_mic=None, audio_file_upload=None, language="eng"):
33
  transcription = processor.decode(ids)
34
  return transcription
35
 
36
- languages = list(processor.tokenizer.vocab.keys())
37
-
38
- examples = [["kab_1.mp3", None, "kab"],
39
- ["kab_2.mp3", None, "kab"]]
40
 
41
  description = '''Automatic Speech Recognition with [MMS](https://ai.facebook.com/blog/multilingual-model-speech-recognition/) (Massively Multilingual Speech) by Meta.
42
  Supports [1162 languages](https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html). Read the paper for more details: [Scaling Speech Technology to 1,000+ Languages](https://arxiv.org/abs/2305.13516).'''
@@ -45,7 +50,7 @@ iface = gr.Interface(fn=transcribe,
45
  inputs=[
46
  gr.Audio(source="microphone", type="filepath", label="Record Audio"),
47
  gr.Audio(source="upload", type="filepath", label="Upload Audio"),
48
- gr.Dropdown(choices=languages, label="Language", value="eng")
49
  ],
50
  outputs=gr.Textbox(label="Transcription"),
51
  examples=examples,
 
2
  from transformers import Wav2Vec2ForCTC, AutoProcessor
3
  import torch
4
  import librosa
5
+ import json
6
+
7
+ with open('ISO_codes.json', 'r') as file:
8
+ iso_codes = json.load(file)
9
+
10
+ languages = list(iso_codes.keys())
11
 
12
  model_id = "facebook/mms-1b-all"
13
  processor = AutoProcessor.from_pretrained(model_id)
14
  model = Wav2Vec2ForCTC.from_pretrained(model_id)
15
 
16
+ def transcribe(audio_file_mic=None, audio_file_upload=None, language="English (eng)"):
17
  if audio_file_mic:
18
  audio_file = audio_file_mic
19
  elif audio_file_upload:
 
27
  speech = librosa.resample(speech, orig_sr=sample_rate, target_sr=16000)
28
 
29
  # Keep the same model in memory and simply switch out the language adapters by calling load_adapter() for the model and set_target_lang() for the tokenizer
30
+ language_code = iso_codes[language]
31
+ processor.tokenizer.set_target_lang(language_code)
32
+ model.load_adapter(language_code)
33
 
34
  inputs = processor(speech, sampling_rate=16_000, return_tensors="pt")
35
 
 
40
  transcription = processor.decode(ids)
41
  return transcription
42
 
43
+ examples = [["kab_1.mp3", None, "Amazigh (kab)"],
44
+ ["kab_2.mp3", None, "Amazigh (kab)"]]
 
 
45
 
46
  description = '''Automatic Speech Recognition with [MMS](https://ai.facebook.com/blog/multilingual-model-speech-recognition/) (Massively Multilingual Speech) by Meta.
47
  Supports [1162 languages](https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html). Read the paper for more details: [Scaling Speech Technology to 1,000+ Languages](https://arxiv.org/abs/2305.13516).'''
 
50
  inputs=[
51
  gr.Audio(source="microphone", type="filepath", label="Record Audio"),
52
  gr.Audio(source="upload", type="filepath", label="Upload Audio"),
53
+ gr.Dropdown(choices=languages, label="Language", value="English (eng)")
54
  ],
55
  outputs=gr.Textbox(label="Transcription"),
56
  examples=examples,