sanchit-gandhi HF staff commited on
Commit
c47407b
1 Parent(s): 312352e

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 +39 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "|",
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": "ctu",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "|",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 36,
3
+ "'": 11,
4
+ "a": 2,
5
+ "b": 10,
6
+ "c": 3,
7
+ "d": 24,
8
+ "e": 6,
9
+ "f": 31,
10
+ "g": 26,
11
+ "h": 16,
12
+ "i": 1,
13
+ "j": 8,
14
+ "k": 35,
15
+ "l": 4,
16
+ "m": 12,
17
+ "n": 9,
18
+ "o": 7,
19
+ "p": 19,
20
+ "q": 21,
21
+ "r": 23,
22
+ "s": 14,
23
+ "t": 5,
24
+ "u": 13,
25
+ "v": 33,
26
+ "w": 20,
27
+ "x": 22,
28
+ "y": 17,
29
+ "z": 32,
30
+ "|": 0,
31
+ "á": 28,
32
+ "é": 29,
33
+ "í": 27,
34
+ "ñ": 18,
35
+ "ó": 30,
36
+ "ú": 25,
37
+ "ń": 34,
38
+ "ʌ": 15
39
+ }