wav2vec2-bert-CV16-en / tokenizer.json
Xenova's picture
Xenova HF staff
Upload tokenizer.json
42e9268 verified
raw
history blame
2.21 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 2,
"content": "</s>",
"single_word": false,
"lstrip": true,
"rstrip": true,
"normalized": false,
"special": true
},
{
"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": 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": {
"'": 5,
"-": 6,
"</s>": 2,
"<pad>": 0,
"<s>": 1,
"<unk>": 3,
"a": 7,
"b": 8,
"c": 9,
"d": 10,
"e": 11,
"f": 12,
"g": 13,
"h": 14,
"i": 15,
"j": 16,
"k": 17,
"l": 18,
"m": 19,
"n": 20,
"o": 21,
"p": 22,
"q": 23,
"r": 24,
"s": 25,
"t": 26,
"u": 27,
"v": 28,
"w": 29,
"x": 30,
"y": 31,
"z": 32,
"|": 4
}
}
}