sanchit-gandhi HF staff commited on
Commit
e49561f
1 Parent(s): 15ef5f6

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +4 -0
  2. tokenizer_config.json +12 -0
  3. vocab.json +51 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "0",
3
+ "unk_token": "<unk>"
4
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "is_uroman": false,
5
+ "language": "bor",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "0",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 30,
3
+ "'": 39,
4
+ "0": 0,
5
+ "1": 42,
6
+ "2": 29,
7
+ "3": 28,
8
+ "4": 18,
9
+ "5": 37,
10
+ "6": 19,
11
+ "7": 40,
12
+ "_": 27,
13
+ "a": 1,
14
+ "b": 7,
15
+ "c": 44,
16
+ "d": 9,
17
+ "e": 16,
18
+ "f": 25,
19
+ "g": 5,
20
+ "h": 20,
21
+ "i": 31,
22
+ "j": 38,
23
+ "k": 15,
24
+ "l": 17,
25
+ "m": 11,
26
+ "n": 26,
27
+ "o": 8,
28
+ "p": 45,
29
+ "q": 10,
30
+ "r": 23,
31
+ "s": 14,
32
+ "t": 48,
33
+ "u": 43,
34
+ "v": 12,
35
+ "w": 4,
36
+ "x": 22,
37
+ "z": 41,
38
+ "á": 24,
39
+ "â": 46,
40
+ "ã": 21,
41
+ "ç": 13,
42
+ "é": 3,
43
+ "ê": 6,
44
+ "í": 33,
45
+ "ó": 32,
46
+ "ô": 35,
47
+ "ú": 47,
48
+ "ü": 34,
49
+ "č": 2,
50
+ "–": 36
51
+ }