codebyzeb's picture
Upload tokenizer
2b4611b verified
raw
history blame
1.96 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "UNK",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "PAD",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 5,
"content": "UTT_BOUNDARY",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Replace",
"pattern": {
"String": "\n"
},
"content": " UTT_BOUNDARY"
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
}
]
},
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": null,
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"UNK": 0,
"PAD": 1,
"BOS": 2,
"EOS": 3,
"WORD_BOUNDARY": 4,
"UTT_BOUNDARY": 5,
"k": 6,
"y": 7,
"m": 8,
"aɪ": 9,
"s": 10,
"t": 11,
"eɪ": 12,
"ŋ": 13,
"a": 14,
"i": 15,
"n": 16,
"ɛ": 17,
"æ": 18,
"z": 19,
"ɡ": 20,
"r": 21,
"v": 22,
"u": 23,
"ɾ": 24,
"d": 25,
"ʊ": 26,
"oɪ": 27,
"ɲ": 28,
"e": 29,
"f": 30,
"o": 31,
"p": 32,
"ʒ": 33,
"t̠ʃ": 34,
"d̠ʒ": 35,
"eʊ": 36,
"w": 37,
"aʊ": 38,
"j": 39,
"ə": 40,
"ũ": 41,
"ɐ̃": 42,
"l": 43,
"b": 44,
"x": 45,
"ɔ": 46,
"ʃ": 47,
"iʊ": 48,
"ɛʊ": 49,
"ɔɪ": 50,
"uɪ": 51
},
"unk_token": "UNK"
}
}