sanchit-gandhi HF staff commited on
Commit
f488e5d
1 Parent(s): 21337bb

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