auliaadila commited on
Commit
9d14812
1 Parent(s): 4d94079

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +13 -0
  3. vocab.json +41 -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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 25,
3
+ "1": 3,
4
+ "2": 6,
5
+ "3": 14,
6
+ "4": 17,
7
+ "5": 22,
8
+ "6": 23,
9
+ "7": 7,
10
+ "8": 35,
11
+ "9": 32,
12
+ "[PAD]": 38,
13
+ "[UNK]": 37,
14
+ "a": 1,
15
+ "b": 29,
16
+ "c": 36,
17
+ "d": 5,
18
+ "e": 11,
19
+ "f": 26,
20
+ "g": 4,
21
+ "h": 16,
22
+ "i": 10,
23
+ "j": 2,
24
+ "k": 19,
25
+ "l": 28,
26
+ "m": 18,
27
+ "n": 24,
28
+ "o": 20,
29
+ "p": 0,
30
+ "q": 30,
31
+ "r": 33,
32
+ "s": 15,
33
+ "t": 13,
34
+ "u": 21,
35
+ "v": 8,
36
+ "w": 12,
37
+ "x": 34,
38
+ "y": 31,
39
+ "z": 27,
40
+ "|": 9
41
+ }