seq2seq-amharic / vocab.json
Samuael's picture
Upload tokenizer
ff1e6f5
{
" ": 1,
"!": 272,
"#": 302,
"%": 278,
"(": 275,
")": 280,
"*": 301,
"+": 283,
"-": 285,
".": 282,
"/": 287,
"0": 288,
"1": 289,
"2": 290,
"3": 291,
"4": 292,
"5": 293,
"6": 294,
"7": 295,
"8": 296,
"9": 297,
"<BOS>": 2,
"<EOS>": 3,
"<pad>": 0,
"?": 303,
"«": 276,
"»": 279,
"ሀ": 4,
"ሁ": 5,
"ሂ": 6,
"ሃ": 7,
"ሄ": 8,
"ህ": 9,
"ሆ": 10,
"ለ": 11,
"ሉ": 12,
"ሊ": 13,
"ላ": 14,
"ሌ": 15,
"ል": 16,
"ሎ": 17,
"ሏ": 18,
"ሐ": 19,
"ሑ": 20,
"ሒ": 21,
"ሓ": 22,
"ሔ": 23,
"ሕ": 24,
"ሖ": 25,
"መ": 26,
"ሙ": 27,
"ሚ": 28,
"ማ": 29,
"ሜ": 30,
"ም": 31,
"ሞ": 32,
"ሟ": 33,
"ሠ": 34,
"ሡ": 35,
"ሢ": 36,
"ሣ": 37,
"ሤ": 38,
"ሥ": 39,
"ሦ": 40,
"ሧ": 41,
"ረ": 42,
"ሩ": 43,
"ሪ": 44,
"ራ": 45,
"ሬ": 46,
"ር": 47,
"ሮ": 48,
"ሯ": 49,
"ሰ": 50,
"ሱ": 51,
"ሲ": 52,
"ሳ": 53,
"ሴ": 54,
"ስ": 55,
"ሶ": 56,
"ሷ": 57,
"ሸ": 58,
"ሹ": 59,
"ሺ": 60,
"ሻ": 61,
"ሼ": 62,
"ሽ": 63,
"ሾ": 64,
"ሿ": 65,
"ቀ": 66,
"ቁ": 67,
"ቂ": 68,
"ቃ": 69,
"ቄ": 70,
"ቅ": 71,
"ቆ": 72,
"ቋ": 73,
"በ": 74,
"ቡ": 75,
"ቢ": 76,
"ባ": 77,
"ቤ": 78,
"ብ": 79,
"ቦ": 80,
"ቧ": 81,
"ቨ": 82,
"ቩ": 83,
"ቪ": 84,
"ቫ": 85,
"ቬ": 86,
"ቭ": 87,
"ቮ": 88,
"ቯ": 89,
"ተ": 90,
"ቱ": 91,
"ቲ": 92,
"ታ": 93,
"ቴ": 94,
"ት": 95,
"ቶ": 96,
"ቷ": 97,
"ቸ": 98,
"ቹ": 99,
"ቺ": 100,
"ቻ": 101,
"ቼ": 102,
"ች": 103,
"ቾ": 104,
"ቿ": 105,
"ኀ": 106,
"ኁ": 107,
"ኂ": 108,
"ኃ": 109,
"ኄ": 110,
"ኅ": 111,
"ኋ": 112,
"ነ": 113,
"ኑ": 114,
"ኒ": 115,
"ና": 116,
"ኔ": 117,
"ን": 118,
"ኖ": 119,
"ኗ": 120,
"ኘ": 121,
"ኙ": 122,
"ኚ": 123,
"ኛ": 124,
"ኜ": 125,
"ኝ": 126,
"ኞ": 127,
"ኟ": 128,
"አ": 129,
"ኡ": 130,
"ኢ": 131,
"ኣ": 132,
"ኤ": 133,
"እ": 134,
"ኦ": 135,
"ኧ": 136,
"ከ": 137,
"ኩ": 138,
"ኪ": 139,
"ካ": 140,
"ኬ": 141,
"ክ": 142,
"ኮ": 143,
"ኳ": 144,
"ኸ": 145,
"ኹ": 146,
"ኺ": 147,
"ኻ": 148,
"ኼ": 149,
"ኽ": 150,
"ኾ": 151,
"ዀ": 152,
"ዃ": 153,
"ወ": 154,
"ዉ": 155,
"ዊ": 156,
"ዋ": 157,
"ዌ": 158,
"ው": 159,
"ዎ": 160,
"ዏ": 161,
"ዐ": 162,
"ዑ": 163,
"ዒ": 164,
"ዓ": 165,
"ዔ": 166,
"ዕ": 167,
"ዖ": 168,
"ዘ": 169,
"ዙ": 170,
"ዚ": 171,
"ዛ": 172,
"ዜ": 173,
"ዝ": 174,
"ዞ": 175,
"ዟ": 176,
"ዠ": 177,
"ዡ": 178,
"ዢ": 179,
"ዣ": 180,
"ዤ": 181,
"ዥ": 182,
"ዦ": 183,
"ዧ": 184,
"የ": 185,
"ዩ": 186,
"ዪ": 187,
"ያ": 188,
"ዬ": 189,
"ይ": 190,
"ዮ": 191,
"ደ": 192,
"ዱ": 193,
"ዲ": 194,
"ዳ": 195,
"ዴ": 196,
"ድ": 197,
"ዶ": 198,
"ዷ": 199,
"ጀ": 200,
"ጁ": 201,
"ጂ": 202,
"ጃ": 203,
"ጄ": 204,
"ጅ": 205,
"ጆ": 206,
"ጇ": 207,
"ገ": 208,
"ጉ": 209,
"ጊ": 210,
"ጋ": 211,
"ጌ": 212,
"ግ": 213,
"ጎ": 214,
"ጓ": 215,
"ጠ": 216,
"ጡ": 217,
"ጢ": 218,
"ጣ": 219,
"ጤ": 220,
"ጥ": 221,
"ጦ": 222,
"ጧ": 223,
"ጨ": 224,
"ጩ": 225,
"ጪ": 226,
"ጫ": 227,
"ጬ": 228,
"ጭ": 229,
"ጮ": 230,
"ጯ": 231,
"ጰ": 232,
"ጱ": 233,
"ጲ": 234,
"ጳ": 235,
"ጴ": 236,
"ጵ": 237,
"ጶ": 238,
"ጷ": 239,
"ጸ": 240,
"ጹ": 241,
"ጺ": 242,
"ጻ": 243,
"ጼ": 244,
"ጽ": 245,
"ጾ": 246,
"ጿ": 247,
"ፀ": 248,
"ፁ": 249,
"ፂ": 250,
"ፃ": 251,
"ፄ": 252,
"ፅ": 253,
"ፆ": 254,
"ፇ": 255,
"ፈ": 256,
"ፉ": 257,
"ፊ": 258,
"ፋ": 259,
"ፌ": 260,
"ፍ": 261,
"ፎ": 262,
"ፏ": 263,
"ፐ": 264,
"ፑ": 265,
"ፒ": 266,
"ፓ": 267,
"ፔ": 268,
"ፕ": 269,
"ፖ": 270,
"ፗ": 271,
"፝": 300,
"፡": 298,
"።": 286,
"፣": 284,
"፤": 299,
"፥": 277,
"፦": 273,
"‹": 274,
"›": 281
}