g2pt-moses-small-deg / tokenizer.json
xchen16's picture
Upload tokenizer
0c3e2a9 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 48,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 49,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 50,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 51,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 52,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": []
},
"pre_tokenizer": {
"type": "WhitespaceSplit"
},
"post_processor": null,
"decoder": {
"type": "WordPiece",
"prefix": "##",
"cleanup": true
},
"model": {
"type": "WordLevel",
"vocab": {
"<boc>": 0,
"<eoc>": 1,
"<sepc>": 2,
"<bog>": 3,
"<eog>": 4,
"<sepg>": 5,
"IDX_0": 6,
"IDX_1": 7,
"IDX_2": 8,
"IDX_3": 9,
"IDX_4": 10,
"IDX_5": 11,
"IDX_6": 12,
"IDX_7": 13,
"IDX_8": 14,
"IDX_9": 15,
"IDX_10": 16,
"IDX_11": 17,
"IDX_12": 18,
"IDX_13": 19,
"IDX_14": 20,
"IDX_15": 21,
"IDX_16": 22,
"IDX_17": 23,
"IDX_18": 24,
"IDX_19": 25,
"IDX_20": 26,
"IDX_21": 27,
"IDX_22": 28,
"IDX_23": 29,
"IDX_24": 30,
"IDX_25": 31,
"IDX_26": 32,
"IDX_27": 33,
"IDX_28": 34,
"IDX_29": 35,
"ATOM_C": 36,
"ATOM_N": 37,
"ATOM_O": 38,
"ATOM_F": 39,
"ATOM_S": 40,
"ATOM_Cl": 41,
"ATOM_Br": 42,
"ATOM_H": 43,
"BOND_SINGLE": 44,
"BOND_DOUBLE": 45,
"BOND_TRIPLE": 46,
"BOND_AROMATIC": 47
},
"unk_token": "[UNK]"
}
}