sanchit-gandhi HF staff commited on
Commit
ccff38d
1 Parent(s): 97bbb4b

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 +38 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "9",
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": "crs",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "9",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 2,
3
+ "'": 21,
4
+ "-": 31,
5
+ "0": 18,
6
+ "1": 29,
7
+ "2": 10,
8
+ "3": 33,
9
+ "4": 12,
10
+ "5": 6,
11
+ "6": 34,
12
+ "7": 19,
13
+ "8": 7,
14
+ "9": 0,
15
+ "_": 35,
16
+ "a": 23,
17
+ "b": 16,
18
+ "d": 8,
19
+ "e": 27,
20
+ "f": 22,
21
+ "g": 11,
22
+ "h": 15,
23
+ "i": 30,
24
+ "k": 25,
25
+ "l": 5,
26
+ "m": 14,
27
+ "n": 4,
28
+ "o": 28,
29
+ "p": 24,
30
+ "r": 1,
31
+ "s": 17,
32
+ "t": 9,
33
+ "u": 32,
34
+ "v": 26,
35
+ "w": 20,
36
+ "y": 13,
37
+ "z": 3
38
+ }