sanchit-gandhi HF staff commited on
Commit
30a9a0d
1 Parent(s): 1e01cbf

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 +42 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "l",
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": "crt",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "l",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 15,
3
+ "'": 27,
4
+ "-": 5,
5
+ "0": 32,
6
+ "4": 11,
7
+ "9": 9,
8
+ "_": 25,
9
+ "a": 23,
10
+ "b": 21,
11
+ "c": 6,
12
+ "d": 31,
13
+ "e": 24,
14
+ "f": 28,
15
+ "g": 10,
16
+ "h": 34,
17
+ "i": 39,
18
+ "j": 33,
19
+ "k": 16,
20
+ "l": 0,
21
+ "m": 12,
22
+ "n": 37,
23
+ "o": 26,
24
+ "p": 20,
25
+ "q": 8,
26
+ "r": 7,
27
+ "s": 13,
28
+ "t": 2,
29
+ "u": 35,
30
+ "v": 36,
31
+ "w": 3,
32
+ "x": 19,
33
+ "y": 22,
34
+ "z": 30,
35
+ "á": 14,
36
+ "é": 38,
37
+ "í": 1,
38
+ "ñ": 18,
39
+ "ó": 29,
40
+ "ú": 4,
41
+ "—": 17
42
+ }