Upload 3 files
Browse files- special_tokens_map.json +2 -115
- tokenizer_config.json +1 -13
- vocab.json +1 -430
special_tokens_map.json
CHANGED
|
@@ -1,120 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
{
|
| 4 |
-
"content": "<s>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": true,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "</s>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": true,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"content": "<s>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": true,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"content": "</s>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": true,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
},
|
| 31 |
-
{
|
| 32 |
-
"content": "<s>",
|
| 33 |
-
"lstrip": false,
|
| 34 |
-
"normalized": true,
|
| 35 |
-
"rstrip": false,
|
| 36 |
-
"single_word": false
|
| 37 |
-
},
|
| 38 |
-
{
|
| 39 |
-
"content": "</s>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": true,
|
| 42 |
-
"rstrip": false,
|
| 43 |
-
"single_word": false
|
| 44 |
-
},
|
| 45 |
-
{
|
| 46 |
-
"content": "<s>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": true,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"content": "</s>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": true,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"content": "<s>",
|
| 61 |
-
"lstrip": false,
|
| 62 |
-
"normalized": true,
|
| 63 |
-
"rstrip": false,
|
| 64 |
-
"single_word": false
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"content": "</s>",
|
| 68 |
-
"lstrip": false,
|
| 69 |
-
"normalized": true,
|
| 70 |
-
"rstrip": false,
|
| 71 |
-
"single_word": false
|
| 72 |
-
},
|
| 73 |
-
{
|
| 74 |
-
"content": "<s>",
|
| 75 |
-
"lstrip": false,
|
| 76 |
-
"normalized": true,
|
| 77 |
-
"rstrip": false,
|
| 78 |
-
"single_word": false
|
| 79 |
-
},
|
| 80 |
-
{
|
| 81 |
-
"content": "</s>",
|
| 82 |
-
"lstrip": false,
|
| 83 |
-
"normalized": true,
|
| 84 |
-
"rstrip": false,
|
| 85 |
-
"single_word": false
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"content": "<s>",
|
| 89 |
-
"lstrip": false,
|
| 90 |
-
"normalized": true,
|
| 91 |
-
"rstrip": false,
|
| 92 |
-
"single_word": false
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"content": "</s>",
|
| 96 |
-
"lstrip": false,
|
| 97 |
-
"normalized": true,
|
| 98 |
-
"rstrip": false,
|
| 99 |
-
"single_word": false
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"content": "<s>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": true,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false
|
| 107 |
-
},
|
| 108 |
-
{
|
| 109 |
-
"content": "</s>",
|
| 110 |
-
"lstrip": false,
|
| 111 |
-
"normalized": true,
|
| 112 |
-
"rstrip": false,
|
| 113 |
-
"single_word": false
|
| 114 |
-
}
|
| 115 |
-
],
|
| 116 |
"bos_token": "<s>",
|
| 117 |
"eos_token": "</s>",
|
| 118 |
"pad_token": "[PAD]",
|
| 119 |
"unk_token": "[UNK]"
|
| 120 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"bos_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
| 5 |
"pad_token": "[PAD]",
|
| 6 |
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1,13 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
-
"clean_up_tokenization_spaces": true,
|
| 4 |
-
"do_lower_case": false,
|
| 5 |
-
"eos_token": "</s>",
|
| 6 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
-
"pad_token": "[PAD]",
|
| 8 |
-
"replace_word_delimiter_char": " ",
|
| 9 |
-
"target_lang": "multilingual_african",
|
| 10 |
-
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 11 |
-
"unk_token": "[UNK]",
|
| 12 |
-
"word_delimiter_token": "|"
|
| 13 |
-
}
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "clean_up_tokenization_spaces": true, "do_lower_case": false, "eos_token": "</s>", "model_max_length": 1000000000000000019884624838656, "pad_token": "[PAD]", "replace_word_delimiter_char": " ", "target_lang": "multilingual_african", "tokenizer_class": "Wav2Vec2CTCTokenizer", "unk_token": "[UNK]", "word_delimiter_token": "|"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vocab.json
CHANGED
|
@@ -1,430 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"multilingual_african": {
|
| 3 |
-
"<": 1,
|
| 4 |
-
"=": 2,
|
| 5 |
-
">": 3,
|
| 6 |
-
"[": 4,
|
| 7 |
-
"[PAD]": 425,
|
| 8 |
-
"[UNK]": 424,
|
| 9 |
-
"\\": 5,
|
| 10 |
-
"]": 6,
|
| 11 |
-
"_": 7,
|
| 12 |
-
"`": 8,
|
| 13 |
-
"a": 9,
|
| 14 |
-
"b": 10,
|
| 15 |
-
"c": 11,
|
| 16 |
-
"d": 12,
|
| 17 |
-
"e": 13,
|
| 18 |
-
"f": 14,
|
| 19 |
-
"g": 15,
|
| 20 |
-
"h": 16,
|
| 21 |
-
"i": 17,
|
| 22 |
-
"j": 18,
|
| 23 |
-
"k": 19,
|
| 24 |
-
"l": 20,
|
| 25 |
-
"m": 21,
|
| 26 |
-
"n": 22,
|
| 27 |
-
"o": 23,
|
| 28 |
-
"p": 24,
|
| 29 |
-
"q": 25,
|
| 30 |
-
"r": 26,
|
| 31 |
-
"s": 27,
|
| 32 |
-
"t": 28,
|
| 33 |
-
"u": 29,
|
| 34 |
-
"v": 30,
|
| 35 |
-
"w": 31,
|
| 36 |
-
"x": 32,
|
| 37 |
-
"y": 33,
|
| 38 |
-
"z": 34,
|
| 39 |
-
"|": 0,
|
| 40 |
-
"~": 35,
|
| 41 |
-
"«": 36,
|
| 42 |
-
"²": 37,
|
| 43 |
-
"µ": 38,
|
| 44 |
-
"·": 39,
|
| 45 |
-
"»": 40,
|
| 46 |
-
"à": 41,
|
| 47 |
-
"á": 42,
|
| 48 |
-
"â": 43,
|
| 49 |
-
"ã": 44,
|
| 50 |
-
"ç": 45,
|
| 51 |
-
"è": 46,
|
| 52 |
-
"é": 47,
|
| 53 |
-
"ê": 48,
|
| 54 |
-
"ë": 49,
|
| 55 |
-
"ì": 50,
|
| 56 |
-
"í": 51,
|
| 57 |
-
"ï": 52,
|
| 58 |
-
"ñ": 53,
|
| 59 |
-
"ò": 54,
|
| 60 |
-
"ó": 55,
|
| 61 |
-
"ô": 56,
|
| 62 |
-
"õ": 57,
|
| 63 |
-
"ö": 58,
|
| 64 |
-
"ù": 59,
|
| 65 |
-
"ú": 60,
|
| 66 |
-
"û": 61,
|
| 67 |
-
"ć": 62,
|
| 68 |
-
"č": 63,
|
| 69 |
-
"ĕ": 64,
|
| 70 |
-
"ğ": 65,
|
| 71 |
-
"ĩ": 66,
|
| 72 |
-
"ī": 67,
|
| 73 |
-
"ĭ": 68,
|
| 74 |
-
"ĺ": 69,
|
| 75 |
-
"ń": 70,
|
| 76 |
-
"ŋ": 71,
|
| 77 |
-
"ŏ": 72,
|
| 78 |
-
"ś": 73,
|
| 79 |
-
"š": 74,
|
| 80 |
-
"ŧ": 75,
|
| 81 |
-
"ũ": 76,
|
| 82 |
-
"ŭ": 77,
|
| 83 |
-
"ŵ": 78,
|
| 84 |
-
"ƙ": 79,
|
| 85 |
-
"ƥ": 80,
|
| 86 |
-
"ƭ": 81,
|
| 87 |
-
"ƴ": 82,
|
| 88 |
-
"ǧ": 83,
|
| 89 |
-
"ǹ": 84,
|
| 90 |
-
"ɓ": 85,
|
| 91 |
-
"ɔ": 86,
|
| 92 |
-
"ɖ": 87,
|
| 93 |
-
"ɗ": 88,
|
| 94 |
-
"ɛ": 89,
|
| 95 |
-
"ɣ": 90,
|
| 96 |
-
"ɲ": 91,
|
| 97 |
-
"ʹ": 92,
|
| 98 |
-
"ʻ": 93,
|
| 99 |
-
"̀": 94,
|
| 100 |
-
"́": 95,
|
| 101 |
-
"̆": 96,
|
| 102 |
-
"̈": 97,
|
| 103 |
-
"̣": 98,
|
| 104 |
-
"έ": 99,
|
| 105 |
-
"γ": 100,
|
| 106 |
-
"ε": 101,
|
| 107 |
-
"ԑ": 102,
|
| 108 |
-
"ሀ": 103,
|
| 109 |
-
"ሁ": 104,
|
| 110 |
-
"ሂ": 105,
|
| 111 |
-
"ሃ": 106,
|
| 112 |
-
"ሄ": 107,
|
| 113 |
-
"ህ": 108,
|
| 114 |
-
"ሆ": 109,
|
| 115 |
-
"ለ": 110,
|
| 116 |
-
"ሉ": 111,
|
| 117 |
-
"ሊ": 112,
|
| 118 |
-
"ላ": 113,
|
| 119 |
-
"ሌ": 114,
|
| 120 |
-
"ል": 115,
|
| 121 |
-
"ሎ": 116,
|
| 122 |
-
"ሏ": 117,
|
| 123 |
-
"ሐ": 118,
|
| 124 |
-
"ሑ": 119,
|
| 125 |
-
"ሒ": 120,
|
| 126 |
-
"ሓ": 121,
|
| 127 |
-
"ሔ": 122,
|
| 128 |
-
"ሕ": 123,
|
| 129 |
-
"ሖ": 124,
|
| 130 |
-
"መ": 125,
|
| 131 |
-
"ሙ": 126,
|
| 132 |
-
"ሚ": 127,
|
| 133 |
-
"ማ": 128,
|
| 134 |
-
"ሜ": 129,
|
| 135 |
-
"ም": 130,
|
| 136 |
-
"ሞ": 131,
|
| 137 |
-
"ሟ": 132,
|
| 138 |
-
"ሠ": 133,
|
| 139 |
-
"ሡ": 134,
|
| 140 |
-
"ሣ": 135,
|
| 141 |
-
"ሥ": 136,
|
| 142 |
-
"ሦ": 137,
|
| 143 |
-
"ረ": 138,
|
| 144 |
-
"ሩ": 139,
|
| 145 |
-
"ሪ": 140,
|
| 146 |
-
"ራ": 141,
|
| 147 |
-
"ሬ": 142,
|
| 148 |
-
"ር": 143,
|
| 149 |
-
"ሮ": 144,
|
| 150 |
-
"ሯ": 145,
|
| 151 |
-
"ሰ": 146,
|
| 152 |
-
"ሱ": 147,
|
| 153 |
-
"ሲ": 148,
|
| 154 |
-
"ሳ": 149,
|
| 155 |
-
"ሴ": 150,
|
| 156 |
-
"ስ": 151,
|
| 157 |
-
"ሶ": 152,
|
| 158 |
-
"ሷ": 153,
|
| 159 |
-
"ሸ": 154,
|
| 160 |
-
"ሹ": 155,
|
| 161 |
-
"ሺ": 156,
|
| 162 |
-
"ሻ": 157,
|
| 163 |
-
"ሼ": 158,
|
| 164 |
-
"ሽ": 159,
|
| 165 |
-
"ሾ": 160,
|
| 166 |
-
"ሿ": 161,
|
| 167 |
-
"ቀ": 162,
|
| 168 |
-
"ቁ": 163,
|
| 169 |
-
"ቂ": 164,
|
| 170 |
-
"ቃ": 165,
|
| 171 |
-
"ቄ": 166,
|
| 172 |
-
"ቅ": 167,
|
| 173 |
-
"ቆ": 168,
|
| 174 |
-
"ቋ": 169,
|
| 175 |
-
"ቐ": 170,
|
| 176 |
-
"ቒ": 171,
|
| 177 |
-
"ቓ": 172,
|
| 178 |
-
"ቕ": 173,
|
| 179 |
-
"ቚ": 174,
|
| 180 |
-
"በ": 175,
|
| 181 |
-
"ቡ": 176,
|
| 182 |
-
"ቢ": 177,
|
| 183 |
-
"ባ": 178,
|
| 184 |
-
"ቤ": 179,
|
| 185 |
-
"ብ": 180,
|
| 186 |
-
"ቦ": 181,
|
| 187 |
-
"ቧ": 182,
|
| 188 |
-
"ቨ": 183,
|
| 189 |
-
"ቩ": 184,
|
| 190 |
-
"ቪ": 185,
|
| 191 |
-
"ቫ": 186,
|
| 192 |
-
"ቬ": 187,
|
| 193 |
-
"ቭ": 188,
|
| 194 |
-
"ቮ": 189,
|
| 195 |
-
"ቯ": 190,
|
| 196 |
-
"ተ": 191,
|
| 197 |
-
"ቱ": 192,
|
| 198 |
-
"ቲ": 193,
|
| 199 |
-
"ታ": 194,
|
| 200 |
-
"ቴ": 195,
|
| 201 |
-
"ት": 196,
|
| 202 |
-
"ቶ": 197,
|
| 203 |
-
"ቷ": 198,
|
| 204 |
-
"ቸ": 199,
|
| 205 |
-
"ቹ": 200,
|
| 206 |
-
"ቺ": 201,
|
| 207 |
-
"ቻ": 202,
|
| 208 |
-
"ቼ": 203,
|
| 209 |
-
"ች": 204,
|
| 210 |
-
"ቾ": 205,
|
| 211 |
-
"ቿ": 206,
|
| 212 |
-
"ኃ": 207,
|
| 213 |
-
"ኅ": 208,
|
| 214 |
-
"ኋ": 209,
|
| 215 |
-
"ነ": 210,
|
| 216 |
-
"ኑ": 211,
|
| 217 |
-
"ኒ": 212,
|
| 218 |
-
"ና": 213,
|
| 219 |
-
"ኔ": 214,
|
| 220 |
-
"ን": 215,
|
| 221 |
-
"ኖ": 216,
|
| 222 |
-
"ኗ": 217,
|
| 223 |
-
"ኘ": 218,
|
| 224 |
-
"ኙ": 219,
|
| 225 |
-
"ኚ": 220,
|
| 226 |
-
"ኛ": 221,
|
| 227 |
-
"ኜ": 222,
|
| 228 |
-
"ኝ": 223,
|
| 229 |
-
"ኞ": 224,
|
| 230 |
-
"ኟ": 225,
|
| 231 |
-
"አ": 226,
|
| 232 |
-
"ኡ": 227,
|
| 233 |
-
"ኢ": 228,
|
| 234 |
-
"ኣ": 229,
|
| 235 |
-
"ኤ": 230,
|
| 236 |
-
"እ": 231,
|
| 237 |
-
"ኦ": 232,
|
| 238 |
-
"ከ": 233,
|
| 239 |
-
"ኩ": 234,
|
| 240 |
-
"ኪ": 235,
|
| 241 |
-
"ካ": 236,
|
| 242 |
-
"ኬ": 237,
|
| 243 |
-
"ክ": 238,
|
| 244 |
-
"ኮ": 239,
|
| 245 |
-
"ኰ": 240,
|
| 246 |
-
"ኲ": 241,
|
| 247 |
-
"ኳ": 242,
|
| 248 |
-
"ኸ": 243,
|
| 249 |
-
"ኻ": 244,
|
| 250 |
-
"ኽ": 245,
|
| 251 |
-
"ኾ": 246,
|
| 252 |
-
"ወ": 247,
|
| 253 |
-
"ዉ": 248,
|
| 254 |
-
"ዊ": 249,
|
| 255 |
-
"ዋ": 250,
|
| 256 |
-
"ዌ": 251,
|
| 257 |
-
"ው": 252,
|
| 258 |
-
"ዎ": 253,
|
| 259 |
-
"ዐ": 254,
|
| 260 |
-
"ዑ": 255,
|
| 261 |
-
"ዒ": 256,
|
| 262 |
-
"ዓ": 257,
|
| 263 |
-
"ዔ": 258,
|
| 264 |
-
"ዕ": 259,
|
| 265 |
-
"ዖ": 260,
|
| 266 |
-
"ዘ": 261,
|
| 267 |
-
"ዙ": 262,
|
| 268 |
-
"ዚ": 263,
|
| 269 |
-
"ዛ": 264,
|
| 270 |
-
"ዜ": 265,
|
| 271 |
-
"ዝ": 266,
|
| 272 |
-
"ዞ": 267,
|
| 273 |
-
"ዟ": 268,
|
| 274 |
-
"ዠ": 269,
|
| 275 |
-
"ዡ": 270,
|
| 276 |
-
"ዢ": 271,
|
| 277 |
-
"ዣ": 272,
|
| 278 |
-
"ዤ": 273,
|
| 279 |
-
"ዥ": 274,
|
| 280 |
-
"ዦ": 275,
|
| 281 |
-
"ዧ": 276,
|
| 282 |
-
"የ": 277,
|
| 283 |
-
"ዩ": 278,
|
| 284 |
-
"ዪ": 279,
|
| 285 |
-
"ያ": 280,
|
| 286 |
-
"ዬ": 281,
|
| 287 |
-
"ይ": 282,
|
| 288 |
-
"ዮ": 283,
|
| 289 |
-
"ደ": 284,
|
| 290 |
-
"ዱ": 285,
|
| 291 |
-
"ዲ": 286,
|
| 292 |
-
"ዳ": 287,
|
| 293 |
-
"ዴ": 288,
|
| 294 |
-
"ድ": 289,
|
| 295 |
-
"ዶ": 290,
|
| 296 |
-
"ዷ": 291,
|
| 297 |
-
"ጀ": 292,
|
| 298 |
-
"ጁ": 293,
|
| 299 |
-
"ጂ": 294,
|
| 300 |
-
"ጃ": 295,
|
| 301 |
-
"ጄ": 296,
|
| 302 |
-
"ጅ": 297,
|
| 303 |
-
"ጆ": 298,
|
| 304 |
-
"ጇ": 299,
|
| 305 |
-
"ገ": 300,
|
| 306 |
-
"ጉ": 301,
|
| 307 |
-
"ጊ": 302,
|
| 308 |
-
"ጋ": 303,
|
| 309 |
-
"ጌ": 304,
|
| 310 |
-
"ግ": 305,
|
| 311 |
-
"ጎ": 306,
|
| 312 |
-
"ጐ": 307,
|
| 313 |
-
"ጓ": 308,
|
| 314 |
-
"ጔ": 309,
|
| 315 |
-
"ጠ": 310,
|
| 316 |
-
"ጡ": 311,
|
| 317 |
-
"ጢ": 312,
|
| 318 |
-
"ጣ": 313,
|
| 319 |
-
"ጤ": 314,
|
| 320 |
-
"ጥ": 315,
|
| 321 |
-
"ጦ": 316,
|
| 322 |
-
"ጧ": 317,
|
| 323 |
-
"ጨ": 318,
|
| 324 |
-
"ጩ": 319,
|
| 325 |
-
"ጪ": 320,
|
| 326 |
-
"ጫ": 321,
|
| 327 |
-
"ጬ": 322,
|
| 328 |
-
"ጭ": 323,
|
| 329 |
-
"ጮ": 324,
|
| 330 |
-
"ጯ": 325,
|
| 331 |
-
"ጰ": 326,
|
| 332 |
-
"ጱ": 327,
|
| 333 |
-
"ጲ": 328,
|
| 334 |
-
"ጳ": 329,
|
| 335 |
-
"ጴ": 330,
|
| 336 |
-
"ጵ": 331,
|
| 337 |
-
"ጶ": 332,
|
| 338 |
-
"ጸ": 333,
|
| 339 |
-
"ጹ": 334,
|
| 340 |
-
"ጺ": 335,
|
| 341 |
-
"ጻ": 336,
|
| 342 |
-
"ጼ": 337,
|
| 343 |
-
"ጽ": 338,
|
| 344 |
-
"ጾ": 339,
|
| 345 |
-
"ጿ": 340,
|
| 346 |
-
"ፀ": 341,
|
| 347 |
-
"ፁ": 342,
|
| 348 |
-
"ፃ": 343,
|
| 349 |
-
"ፅ": 344,
|
| 350 |
-
"ፈ": 345,
|
| 351 |
-
"ፉ": 346,
|
| 352 |
-
"ፊ": 347,
|
| 353 |
-
"ፋ": 348,
|
| 354 |
-
"ፌ": 349,
|
| 355 |
-
"ፍ": 350,
|
| 356 |
-
"ፎ": 351,
|
| 357 |
-
"ፏ": 352,
|
| 358 |
-
"ፐ": 353,
|
| 359 |
-
"ፑ": 354,
|
| 360 |
-
"ፒ": 355,
|
| 361 |
-
"ፓ": 356,
|
| 362 |
-
"ፔ": 357,
|
| 363 |
-
"ፕ": 358,
|
| 364 |
-
"ፖ": 359,
|
| 365 |
-
"፡": 360,
|
| 366 |
-
"።": 361,
|
| 367 |
-
"፣": 362,
|
| 368 |
-
"፤": 363,
|
| 369 |
-
"ḅ": 364,
|
| 370 |
-
"ḍ": 365,
|
| 371 |
-
"ḓ": 366,
|
| 372 |
-
"ḥ": 367,
|
| 373 |
-
"ḷ": 368,
|
| 374 |
-
"ḽ": 369,
|
| 375 |
-
"ṅ": 370,
|
| 376 |
-
"ṋ": 371,
|
| 377 |
-
"ṕ": 372,
|
| 378 |
-
"ṛ": 373,
|
| 379 |
-
"ṣ": 374,
|
| 380 |
-
"ṭ": 375,
|
| 381 |
-
"ṱ": 376,
|
| 382 |
-
"ẃ": 377,
|
| 383 |
-
"ẓ": 378,
|
| 384 |
-
"ạ": 379,
|
| 385 |
-
"ẹ": 380,
|
| 386 |
-
"ị": 381,
|
| 387 |
-
"ọ": 382,
|
| 388 |
-
"ụ": 383,
|
| 389 |
-
"ὲ": 384,
|
| 390 |
-
"–": 385,
|
| 391 |
-
"—": 386,
|
| 392 |
-
"’": 387,
|
| 393 |
-
"‟": 388,
|
| 394 |
-
"•": 389,
|
| 395 |
-
"…": 390,
|
| 396 |
-
"‽": 391,
|
| 397 |
-
"ⴰ": 392,
|
| 398 |
-
"ⴱ": 393,
|
| 399 |
-
"ⴳ": 394,
|
| 400 |
-
"ⴷ": 395,
|
| 401 |
-
"ⴹ": 396,
|
| 402 |
-
"ⴻ": 397,
|
| 403 |
-
"ⴼ": 398,
|
| 404 |
-
"ⴽ": 399,
|
| 405 |
-
"ⵀ": 400,
|
| 406 |
-
"ⵃ": 401,
|
| 407 |
-
"ⵄ": 402,
|
| 408 |
-
"ⵅ": 403,
|
| 409 |
-
"ⵇ": 404,
|
| 410 |
-
"ⵉ": 405,
|
| 411 |
-
"ⵊ": 406,
|
| 412 |
-
"ⵍ": 407,
|
| 413 |
-
"ⵎ": 408,
|
| 414 |
-
"ⵏ": 409,
|
| 415 |
-
"ⵓ": 410,
|
| 416 |
-
"ⵔ": 411,
|
| 417 |
-
"ⵕ": 412,
|
| 418 |
-
"ⵖ": 413,
|
| 419 |
-
"ⵙ": 414,
|
| 420 |
-
"ⵚ": 415,
|
| 421 |
-
"ⵛ": 416,
|
| 422 |
-
"ⵜ": 417,
|
| 423 |
-
"ⵟ": 418,
|
| 424 |
-
"ⵡ": 419,
|
| 425 |
-
"ⵢ": 420,
|
| 426 |
-
"ⵣ": 421,
|
| 427 |
-
"ⵥ": 422,
|
| 428 |
-
"ⵯ": 423
|
| 429 |
-
}
|
| 430 |
-
}
|
|
|
|
| 1 |
+
{"multilingual_african": {"<": 1, "=": 2, ">": 3, "[": 4, "[PAD]": 425, "[UNK]": 424, "\\": 5, "]": 6, "_": 7, "`": 8, "a": 9, "b": 10, "c": 11, "d": 12, "e": 13, "f": 14, "g": 15, "h": 16, "i": 17, "j": 18, "k": 19, "l": 20, "m": 21, "n": 22, "o": 23, "p": 24, "q": 25, "r": 26, "s": 27, "t": 28, "u": 29, "v": 30, "w": 31, "x": 32, "y": 33, "z": 34, "|": 0, "~": 35, "\u00ab": 36, "\u00b2": 37, "\u00b5": 38, "\u00b7": 39, "\u00bb": 40, "\u00e0": 41, "\u00e1": 42, "\u00e2": 43, "\u00e3": 44, "\u00e7": 45, "\u00e8": 46, "\u00e9": 47, "\u00ea": 48, "\u00eb": 49, "\u00ec": 50, "\u00ed": 51, "\u00ef": 52, "\u00f1": 53, "\u00f2": 54, "\u00f3": 55, "\u00f4": 56, "\u00f5": 57, "\u00f6": 58, "\u00f9": 59, "\u00fa": 60, "\u00fb": 61, "\u0107": 62, "\u010d": 63, "\u0115": 64, "\u011f": 65, "\u0129": 66, "\u012b": 67, "\u012d": 68, "\u013a": 69, "\u0144": 70, "\u014b": 71, "\u014f": 72, "\u015b": 73, "\u0161": 74, "\u0167": 75, "\u0169": 76, "\u016d": 77, "\u0175": 78, "\u0199": 79, "\u01a5": 80, "\u01ad": 81, "\u01b4": 82, "\u01e7": 83, "\u01f9": 84, "\u0253": 85, "\u0254": 86, "\u0256": 87, "\u0257": 88, "\u025b": 89, "\u0263": 90, "\u0272": 91, "\u02b9": 92, "\u02bb": 93, "\u0300": 94, "\u0301": 95, "\u0306": 96, "\u0308": 97, "\u0323": 98, "\u03ad": 99, "\u03b3": 100, "\u03b5": 101, "\u0511": 102, "\u1200": 103, "\u1201": 104, "\u1202": 105, "\u1203": 106, "\u1204": 107, "\u1205": 108, "\u1206": 109, "\u1208": 110, "\u1209": 111, "\u120a": 112, "\u120b": 113, "\u120c": 114, "\u120d": 115, "\u120e": 116, "\u120f": 117, "\u1210": 118, "\u1211": 119, "\u1212": 120, "\u1213": 121, "\u1214": 122, "\u1215": 123, "\u1216": 124, "\u1218": 125, "\u1219": 126, "\u121a": 127, "\u121b": 128, "\u121c": 129, "\u121d": 130, "\u121e": 131, "\u121f": 132, "\u1220": 133, "\u1221": 134, "\u1223": 135, "\u1225": 136, "\u1226": 137, "\u1228": 138, "\u1229": 139, "\u122a": 140, "\u122b": 141, "\u122c": 142, "\u122d": 143, "\u122e": 144, "\u122f": 145, "\u1230": 146, "\u1231": 147, "\u1232": 148, "\u1233": 149, "\u1234": 150, "\u1235": 151, "\u1236": 152, "\u1237": 153, "\u1238": 154, "\u1239": 155, "\u123a": 156, "\u123b": 157, "\u123c": 158, "\u123d": 159, "\u123e": 160, "\u123f": 161, "\u1240": 162, "\u1241": 163, "\u1242": 164, "\u1243": 165, "\u1244": 166, "\u1245": 167, "\u1246": 168, "\u124b": 169, "\u1250": 170, "\u1252": 171, "\u1253": 172, "\u1255": 173, "\u125a": 174, "\u1260": 175, "\u1261": 176, "\u1262": 177, "\u1263": 178, "\u1264": 179, "\u1265": 180, "\u1266": 181, "\u1267": 182, "\u1268": 183, "\u1269": 184, "\u126a": 185, "\u126b": 186, "\u126c": 187, "\u126d": 188, "\u126e": 189, "\u126f": 190, "\u1270": 191, "\u1271": 192, "\u1272": 193, "\u1273": 194, "\u1274": 195, "\u1275": 196, "\u1276": 197, "\u1277": 198, "\u1278": 199, "\u1279": 200, "\u127a": 201, "\u127b": 202, "\u127c": 203, "\u127d": 204, "\u127e": 205, "\u127f": 206, "\u1283": 207, "\u1285": 208, "\u128b": 209, "\u1290": 210, "\u1291": 211, "\u1292": 212, "\u1293": 213, "\u1294": 214, "\u1295": 215, "\u1296": 216, "\u1297": 217, "\u1298": 218, "\u1299": 219, "\u129a": 220, "\u129b": 221, "\u129c": 222, "\u129d": 223, "\u129e": 224, "\u129f": 225, "\u12a0": 226, "\u12a1": 227, "\u12a2": 228, "\u12a3": 229, "\u12a4": 230, "\u12a5": 231, "\u12a6": 232, "\u12a8": 233, "\u12a9": 234, "\u12aa": 235, "\u12ab": 236, "\u12ac": 237, "\u12ad": 238, "\u12ae": 239, "\u12b0": 240, "\u12b2": 241, "\u12b3": 242, "\u12b8": 243, "\u12bb": 244, "\u12bd": 245, "\u12be": 246, "\u12c8": 247, "\u12c9": 248, "\u12ca": 249, "\u12cb": 250, "\u12cc": 251, "\u12cd": 252, "\u12ce": 253, "\u12d0": 254, "\u12d1": 255, "\u12d2": 256, "\u12d3": 257, "\u12d4": 258, "\u12d5": 259, "\u12d6": 260, "\u12d8": 261, "\u12d9": 262, "\u12da": 263, "\u12db": 264, "\u12dc": 265, "\u12dd": 266, "\u12de": 267, "\u12df": 268, "\u12e0": 269, "\u12e1": 270, "\u12e2": 271, "\u12e3": 272, "\u12e4": 273, "\u12e5": 274, "\u12e6": 275, "\u12e7": 276, "\u12e8": 277, "\u12e9": 278, "\u12ea": 279, "\u12eb": 280, "\u12ec": 281, "\u12ed": 282, "\u12ee": 283, "\u12f0": 284, "\u12f1": 285, "\u12f2": 286, "\u12f3": 287, "\u12f4": 288, "\u12f5": 289, "\u12f6": 290, "\u12f7": 291, "\u1300": 292, "\u1301": 293, "\u1302": 294, "\u1303": 295, "\u1304": 296, "\u1305": 297, "\u1306": 298, "\u1307": 299, "\u1308": 300, "\u1309": 301, "\u130a": 302, "\u130b": 303, "\u130c": 304, "\u130d": 305, "\u130e": 306, "\u1310": 307, "\u1313": 308, "\u1314": 309, "\u1320": 310, "\u1321": 311, "\u1322": 312, "\u1323": 313, "\u1324": 314, "\u1325": 315, "\u1326": 316, "\u1327": 317, "\u1328": 318, "\u1329": 319, "\u132a": 320, "\u132b": 321, "\u132c": 322, "\u132d": 323, "\u132e": 324, "\u132f": 325, "\u1330": 326, "\u1331": 327, "\u1332": 328, "\u1333": 329, "\u1334": 330, "\u1335": 331, "\u1336": 332, "\u1338": 333, "\u1339": 334, "\u133a": 335, "\u133b": 336, "\u133c": 337, "\u133d": 338, "\u133e": 339, "\u133f": 340, "\u1340": 341, "\u1341": 342, "\u1343": 343, "\u1345": 344, "\u1348": 345, "\u1349": 346, "\u134a": 347, "\u134b": 348, "\u134c": 349, "\u134d": 350, "\u134e": 351, "\u134f": 352, "\u1350": 353, "\u1351": 354, "\u1352": 355, "\u1353": 356, "\u1354": 357, "\u1355": 358, "\u1356": 359, "\u1361": 360, "\u1362": 361, "\u1363": 362, "\u1364": 363, "\u1e05": 364, "\u1e0d": 365, "\u1e13": 366, "\u1e25": 367, "\u1e37": 368, "\u1e3d": 369, "\u1e45": 370, "\u1e4b": 371, "\u1e55": 372, "\u1e5b": 373, "\u1e63": 374, "\u1e6d": 375, "\u1e71": 376, "\u1e83": 377, "\u1e93": 378, "\u1ea1": 379, "\u1eb9": 380, "\u1ecb": 381, "\u1ecd": 382, "\u1ee5": 383, "\u1f72": 384, "\u2013": 385, "\u2014": 386, "\u2019": 387, "\u201f": 388, "\u2022": 389, "\u2026": 390, "\u203d": 391, "\u2d30": 392, "\u2d31": 393, "\u2d33": 394, "\u2d37": 395, "\u2d39": 396, "\u2d3b": 397, "\u2d3c": 398, "\u2d3d": 399, "\u2d40": 400, "\u2d43": 401, "\u2d44": 402, "\u2d45": 403, "\u2d47": 404, "\u2d49": 405, "\u2d4a": 406, "\u2d4d": 407, "\u2d4e": 408, "\u2d4f": 409, "\u2d53": 410, "\u2d54": 411, "\u2d55": 412, "\u2d56": 413, "\u2d59": 414, "\u2d5a": 415, "\u2d5b": 416, "\u2d5c": 417, "\u2d5f": 418, "\u2d61": 419, "\u2d62": 420, "\u2d63": 421, "\u2d65": 422, "\u2d6f": 423}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|