sanchit-gandhi HF staff commited on
Commit
c344b12
1 Parent(s): 5ce88c8

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 +32 -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": "cnh",
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 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 9,
3
+ "'": 18,
4
+ "-": 14,
5
+ "_": 15,
6
+ "a": 8,
7
+ "b": 23,
8
+ "c": 20,
9
+ "d": 26,
10
+ "e": 2,
11
+ "f": 3,
12
+ "g": 5,
13
+ "h": 28,
14
+ "i": 0,
15
+ "j": 11,
16
+ "k": 19,
17
+ "l": 16,
18
+ "m": 7,
19
+ "n": 1,
20
+ "o": 10,
21
+ "p": 4,
22
+ "r": 29,
23
+ "s": 24,
24
+ "t": 12,
25
+ "u": 27,
26
+ "v": 25,
27
+ "w": 6,
28
+ "y": 13,
29
+ "z": 17,
30
+ "ṭ": 21,
31
+ "—": 22
32
+ }