w2v-bert-2.0-Amharic / vocab.json
Bedru's picture
Upload tokenizer
e52795a verified
raw
history blame
4.05 kB
{
"$": 1,
"&": 2,
"+": 3,
"/": 4,
"0": 5,
"1": 6,
"2": 7,
"3": 8,
"4": 9,
"5": 10,
"6": 11,
"7": 12,
"8": 13,
"9": 14,
"[": 15,
"[PAD]": 302,
"[UNK]": 301,
"]": 16,
"a": 17,
"b": 18,
"c": 19,
"d": 20,
"e": 21,
"f": 22,
"g": 23,
"h": 24,
"i": 25,
"j": 26,
"k": 27,
"m": 28,
"n": 29,
"o": 30,
"p": 31,
"r": 32,
"s": 33,
"t": 34,
"u": 35,
"v": 36,
"x": 37,
"y": 38,
"|": 0,
"~": 39,
"£": 40,
"¥": 41,
"°": 42,
"²": 43,
"½": 44,
"¾": 45,
"ã": 46,
"õ": 47,
"ሀ": 48,
"ሁ": 49,
"ሂ": 50,
"ሃ": 51,
"ሄ": 52,
"ህ": 53,
"ሆ": 54,
"ለ": 55,
"ሉ": 56,
"ሊ": 57,
"ላ": 58,
"ሌ": 59,
"ል": 60,
"ሎ": 61,
"ሏ": 62,
"ሐ": 63,
"ሑ": 64,
"ሓ": 65,
"ሔ": 66,
"ሕ": 67,
"መ": 68,
"ሙ": 69,
"ሚ": 70,
"ማ": 71,
"ሜ": 72,
"ም": 73,
"ሞ": 74,
"ሟ": 75,
"ሠ": 76,
"ሡ": 77,
"ሣ": 78,
"ሥ": 79,
"ሦ": 80,
"ረ": 81,
"ሩ": 82,
"ሪ": 83,
"ራ": 84,
"ሬ": 85,
"ር": 86,
"ሮ": 87,
"ሯ": 88,
"ሰ": 89,
"ሱ": 90,
"ሲ": 91,
"ሳ": 92,
"ሴ": 93,
"ስ": 94,
"ሶ": 95,
"ሷ": 96,
"ሸ": 97,
"ሹ": 98,
"ሺ": 99,
"ሻ": 100,
"ሼ": 101,
"ሽ": 102,
"ሾ": 103,
"ሿ": 104,
"ቀ": 105,
"ቁ": 106,
"ቂ": 107,
"ቃ": 108,
"ቄ": 109,
"ቅ": 110,
"ቆ": 111,
"ቋ": 112,
"በ": 113,
"ቡ": 114,
"ቢ": 115,
"ባ": 116,
"ቤ": 117,
"ብ": 118,
"ቦ": 119,
"ቧ": 120,
"ቨ": 121,
"ቪ": 122,
"ቫ": 123,
"ቬ": 124,
"ቭ": 125,
"ቮ": 126,
"ተ": 127,
"ቱ": 128,
"ቲ": 129,
"ታ": 130,
"ቴ": 131,
"ት": 132,
"ቶ": 133,
"ቷ": 134,
"ቸ": 135,
"ቹ": 136,
"ቺ": 137,
"ቻ": 138,
"ቼ": 139,
"ች": 140,
"ቾ": 141,
"ቿ": 142,
"ኀ": 143,
"ኃ": 144,
"ኅ": 145,
"ኋ": 146,
"ነ": 147,
"ኑ": 148,
"ኒ": 149,
"ና": 150,
"ኔ": 151,
"ን": 152,
"ኖ": 153,
"ኗ": 154,
"ኘ": 155,
"ኙ": 156,
"ኚ": 157,
"ኛ": 158,
"ኜ": 159,
"ኝ": 160,
"ኞ": 161,
"ኟ": 162,
"አ": 163,
"ኡ": 164,
"ኢ": 165,
"ኣ": 166,
"ኤ": 167,
"እ": 168,
"ኦ": 169,
"ከ": 170,
"ኩ": 171,
"ኪ": 172,
"ካ": 173,
"ኬ": 174,
"ክ": 175,
"ኮ": 176,
"ኰ": 177,
"ኳ": 178,
"ኸ": 179,
"ኺ": 180,
"ኽ": 181,
"ወ": 182,
"ዉ": 183,
"ዊ": 184,
"ዋ": 185,
"ዌ": 186,
"ው": 187,
"ዎ": 188,
"ዐ": 189,
"ዑ": 190,
"ዒ": 191,
"ዓ": 192,
"ዕ": 193,
"ዖ": 194,
"ዘ": 195,
"ዙ": 196,
"ዚ": 197,
"ዛ": 198,
"ዜ": 199,
"ዝ": 200,
"ዞ": 201,
"ዟ": 202,
"ዠ": 203,
"ዡ": 204,
"ዢ": 205,
"ዣ": 206,
"ዤ": 207,
"ዥ": 208,
"ዦ": 209,
"የ": 210,
"ዩ": 211,
"ዪ": 212,
"ያ": 213,
"ዬ": 214,
"ይ": 215,
"ዮ": 216,
"ደ": 217,
"ዱ": 218,
"ዲ": 219,
"ዳ": 220,
"ዴ": 221,
"ድ": 222,
"ዶ": 223,
"ዷ": 224,
"ጀ": 225,
"ጁ": 226,
"ጂ": 227,
"ጃ": 228,
"ጄ": 229,
"ጅ": 230,
"ጆ": 231,
"ጇ": 232,
"ገ": 233,
"ጉ": 234,
"ጊ": 235,
"ጋ": 236,
"ጌ": 237,
"ግ": 238,
"ጎ": 239,
"ጐ": 240,
"ጓ": 241,
"ጠ": 242,
"ጡ": 243,
"ጢ": 244,
"ጣ": 245,
"ጤ": 246,
"ጥ": 247,
"ጦ": 248,
"ጧ": 249,
"ጨ": 250,
"ጩ": 251,
"ጪ": 252,
"ጫ": 253,
"ጬ": 254,
"ጭ": 255,
"ጮ": 256,
"ጲ": 257,
"ጳ": 258,
"ጴ": 259,
"ጵ": 260,
"ጶ": 261,
"ጸ": 262,
"ጹ": 263,
"ጺ": 264,
"ጻ": 265,
"ጽ": 266,
"ጾ": 267,
"ጿ": 268,
"ፀ": 269,
"ፁ": 270,
"ፃ": 271,
"ፅ": 272,
"ፆ": 273,
"ፈ": 274,
"ፉ": 275,
"ፊ": 276,
"ፋ": 277,
"ፌ": 278,
"ፍ": 279,
"ፎ": 280,
"ፏ": 281,
"ፐ": 282,
"ፑ": 283,
"ፒ": 284,
"ፓ": 285,
"ፔ": 286,
"ፕ": 287,
"ፖ": 288,
"ፗ": 289,
"፡": 290,
"።": 291,
"፣": 292,
"፤": 293,
"፥": 294,
"፦": 295,
"–": 296,
"—": 297,
"’": 298,
"‹": 299,
"›": 300
}