sanchit-gandhi commited on
Commit
b9330bb
·
1 Parent(s): 8c5b86d

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