hugo-vanhamme commited on
Commit
f393890
1 Parent(s): 32f9289

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +11 -0
  3. vocab.json +32 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "[PAD]",
7
+ "replace_word_delimiter_char": " ",
8
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
9
+ "unk_token": "[UNK]",
10
+ "word_delimiter_token": "|"
11
+ }
vocab.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 25,
3
+ "A": 11,
4
+ "B": 26,
5
+ "C": 6,
6
+ "D": 9,
7
+ "E": 22,
8
+ "F": 15,
9
+ "G": 12,
10
+ "H": 27,
11
+ "I": 4,
12
+ "J": 10,
13
+ "K": 23,
14
+ "L": 14,
15
+ "M": 7,
16
+ "N": 2,
17
+ "O": 18,
18
+ "P": 21,
19
+ "Q": 24,
20
+ "R": 19,
21
+ "S": 1,
22
+ "T": 20,
23
+ "U": 16,
24
+ "V": 17,
25
+ "W": 13,
26
+ "X": 0,
27
+ "Y": 3,
28
+ "Z": 5,
29
+ "[PAD]": 29,
30
+ "[UNK]": 28,
31
+ "|": 8
32
+ }