sanchit-gandhi commited on
Commit
795d726
·
1 Parent(s): 895652d

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