sanchit-gandhi HF staff commited on
Commit
0b65432
1 Parent(s): ad9a134

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