etonkou commited on
Commit
9178a6c
1 Parent(s): fb08893

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 +42 -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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 30,
3
+ "0": 12,
4
+ "1": 29,
5
+ "2": 32,
6
+ "3": 34,
7
+ "5": 24,
8
+ "6": 5,
9
+ "9": 37,
10
+ "<": 21,
11
+ ">": 15,
12
+ "[PAD]": 39,
13
+ "[UNK]": 38,
14
+ "_": 26,
15
+ "a": 6,
16
+ "b": 33,
17
+ "c": 16,
18
+ "d": 11,
19
+ "e": 7,
20
+ "f": 4,
21
+ "g": 9,
22
+ "h": 0,
23
+ "i": 25,
24
+ "j": 35,
25
+ "k": 13,
26
+ "l": 20,
27
+ "m": 19,
28
+ "n": 2,
29
+ "o": 27,
30
+ "p": 1,
31
+ "q": 36,
32
+ "r": 8,
33
+ "s": 28,
34
+ "t": 10,
35
+ "u": 31,
36
+ "v": 23,
37
+ "w": 17,
38
+ "x": 22,
39
+ "y": 3,
40
+ "z": 14,
41
+ "|": 18
42
+ }