sanchit-gandhi HF staff commited on
Commit
31c2edb
1 Parent(s): 151fa86

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 +45 -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": "mca",
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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 42,
3
+ "'": 8,
4
+ "-": 36,
5
+ "0": 40,
6
+ "1": 38,
7
+ "3": 41,
8
+ "4": 39,
9
+ "a": 3,
10
+ "b": 28,
11
+ "c": 26,
12
+ "d": 25,
13
+ "e": 2,
14
+ "f": 22,
15
+ "g": 29,
16
+ "h": 12,
17
+ "i": 1,
18
+ "j": 7,
19
+ "k": 9,
20
+ "l": 19,
21
+ "m": 18,
22
+ "n": 6,
23
+ "o": 20,
24
+ "p": 16,
25
+ "q": 10,
26
+ "r": 23,
27
+ "s": 11,
28
+ "t": 5,
29
+ "u": 13,
30
+ "v": 35,
31
+ "w": 17,
32
+ "x": 21,
33
+ "y": 15,
34
+ "z": 33,
35
+ "|": 0,
36
+ "á": 34,
37
+ "é": 31,
38
+ "í": 30,
39
+ "ñ": 37,
40
+ "ó": 32,
41
+ "ú": 27,
42
+ "ƚ": 14,
43
+ "ˈ": 4,
44
+ "—": 24
45
+ }