sanchit-gandhi commited on
Commit
e5701c7
·
1 Parent(s): 633803b

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 +46 -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": "mam-dialect_central",
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 43,
3
+ "'": 2,
4
+ "-": 25,
5
+ "0": 35,
6
+ "1": 38,
7
+ "2": 40,
8
+ "3": 41,
9
+ "4": 37,
10
+ "5": 39,
11
+ "6": 36,
12
+ "a": 5,
13
+ "b": 15,
14
+ "c": 20,
15
+ "d": 23,
16
+ "e": 7,
17
+ "f": 31,
18
+ "g": 27,
19
+ "h": 21,
20
+ "i": 3,
21
+ "j": 6,
22
+ "k": 8,
23
+ "l": 9,
24
+ "m": 16,
25
+ "n": 4,
26
+ "o": 12,
27
+ "p": 22,
28
+ "q": 14,
29
+ "r": 24,
30
+ "s": 19,
31
+ "t": 1,
32
+ "u": 11,
33
+ "v": 32,
34
+ "w": 18,
35
+ "x": 13,
36
+ "y": 10,
37
+ "z": 17,
38
+ "|": 0,
39
+ "á": 33,
40
+ "é": 29,
41
+ "í": 30,
42
+ "ñ": 42,
43
+ "ó": 34,
44
+ "ú": 26,
45
+ "ẍ": 28
46
+ }