File size: 2,187 Bytes
b30a09a |
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 |
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<pad>",
"single_word": false,
"lstrip": true,
"rstrip": true,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<s>",
"single_word": false,
"lstrip": true,
"rstrip": true,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "</s>",
"single_word": false,
"lstrip": true,
"rstrip": true,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "<unk>",
"single_word": false,
"lstrip": true,
"rstrip": true,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Replace",
"pattern": {
"String": " "
},
"content": "|"
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": ""
},
"behavior": "Isolated",
"invert": false
},
"post_processor": null,
"decoder": {
"type": "CTC",
"pad_token": "<pad>",
"word_delimiter_token": "|",
"cleanup": true
},
"model": {
"vocab": {
"<pad>": 0,
"<s>": 1,
"</s>": 2,
"<unk>": 3,
"|": 4,
"E": 5,
"T": 6,
"A": 7,
"O": 8,
"N": 9,
"I": 10,
"H": 11,
"S": 12,
"R": 13,
"D": 14,
"L": 15,
"U": 16,
"M": 17,
"W": 18,
"C": 19,
"F": 20,
"G": 21,
"Y": 22,
"P": 23,
"B": 24,
"V": 25,
"K": 26,
"'": 27,
"X": 28,
"J": 29,
"Q": 30,
"Z": 31
}
}
} |