sanchit-gandhi HF staff commited on
Commit
267b185
1 Parent(s): 31d7908

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