ad019el commited on
Commit
5685e15
1 Parent(s): 2a05864

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 +39 -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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "/": 14,
3
+ "0": 6,
4
+ "1": 23,
5
+ "2": 1,
6
+ "7": 2,
7
+ "9": 0,
8
+ "[PAD]": 36,
9
+ "[UNK]": 35,
10
+ "_": 20,
11
+ "a": 9,
12
+ "b": 25,
13
+ "c": 28,
14
+ "d": 31,
15
+ "e": 16,
16
+ "f": 4,
17
+ "g": 10,
18
+ "h": 18,
19
+ "i": 26,
20
+ "j": 8,
21
+ "k": 15,
22
+ "l": 3,
23
+ "m": 21,
24
+ "n": 24,
25
+ "o": 34,
26
+ "p": 12,
27
+ "q": 33,
28
+ "r": 22,
29
+ "s": 29,
30
+ "t": 7,
31
+ "u": 17,
32
+ "v": 32,
33
+ "w": 30,
34
+ "x": 13,
35
+ "y": 11,
36
+ "z": 5,
37
+ "|": 19,
38
+ " ": 27
39
+ }