sanchit-gandhi HF staff commited on
Commit
92289b3
1 Parent(s): 8370c40

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 +40 -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": "mah",
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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 37,
3
+ "'": 32,
4
+ "-": 33,
5
+ "a": 2,
6
+ "b": 14,
7
+ "c": 35,
8
+ "d": 22,
9
+ "e": 1,
10
+ "f": 31,
11
+ "g": 27,
12
+ "h": 30,
13
+ "i": 3,
14
+ "j": 6,
15
+ "k": 5,
16
+ "l": 11,
17
+ "m": 9,
18
+ "n": 4,
19
+ "o": 7,
20
+ "p": 18,
21
+ "q": 36,
22
+ "r": 8,
23
+ "s": 23,
24
+ "t": 12,
25
+ "u": 20,
26
+ "v": 28,
27
+ "w": 13,
28
+ "x": 34,
29
+ "y": 26,
30
+ "z": 29,
31
+ "|": 0,
32
+ "ñ": 16,
33
+ "ā": 17,
34
+ "ō": 10,
35
+ "ū": 25,
36
+ "ḷ": 19,
37
+ "ṃ": 15,
38
+ "ṇ": 24,
39
+ "ọ": 21
40
+ }