auliaadila commited on
Commit
e1676a1
1 Parent(s): 970d6f3

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 +30 -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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 27,
3
+ "[UNK]": 26,
4
+ "a": 20,
5
+ "b": 6,
6
+ "c": 4,
7
+ "d": 12,
8
+ "e": 7,
9
+ "f": 19,
10
+ "g": 11,
11
+ "h": 1,
12
+ "i": 15,
13
+ "j": 0,
14
+ "k": 17,
15
+ "l": 22,
16
+ "m": 13,
17
+ "n": 24,
18
+ "o": 3,
19
+ "p": 16,
20
+ "q": 2,
21
+ "r": 5,
22
+ "s": 21,
23
+ "t": 14,
24
+ "u": 18,
25
+ "v": 23,
26
+ "w": 10,
27
+ "y": 8,
28
+ "z": 25,
29
+ "|": 9
30
+ }