hubert-large-ls960-ft / tokenizer.json
Xenova's picture
Xenova HF staff
Update tokenizer.json
ec40045
{
"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
}
}
}