digicazter commited on
Commit
3758f16
1 Parent(s): b1dcace

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
+ "'": 25,
3
+ "0": 7,
4
+ "1": 23,
5
+ "2": 18,
6
+ "3": 31,
7
+ "5": 33,
8
+ "6": 32,
9
+ "7": 29,
10
+ "8": 27,
11
+ "9": 17,
12
+ "[PAD]": 38,
13
+ "[UNK]": 37,
14
+ "a": 16,
15
+ "b": 22,
16
+ "c": 30,
17
+ "d": 36,
18
+ "e": 11,
19
+ "f": 4,
20
+ "g": 20,
21
+ "h": 28,
22
+ "i": 13,
23
+ "j": 2,
24
+ "k": 35,
25
+ "l": 0,
26
+ "m": 14,
27
+ "n": 15,
28
+ "o": 8,
29
+ "p": 10,
30
+ "q": 1,
31
+ "r": 19,
32
+ "s": 34,
33
+ "t": 5,
34
+ "u": 26,
35
+ "v": 21,
36
+ "w": 12,
37
+ "x": 3,
38
+ "y": 9,
39
+ "z": 24,
40
+ "|": 6
41
+ }