sanchit-gandhi HF staff commited on
Commit
719e541
1 Parent(s): 08c0d8c

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 +33 -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": "zyb",
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 30,
3
+ "'": 26,
4
+ "-": 29,
5
+ "a": 3,
6
+ "b": 16,
7
+ "c": 15,
8
+ "d": 10,
9
+ "e": 2,
10
+ "f": 23,
11
+ "g": 4,
12
+ "h": 6,
13
+ "i": 5,
14
+ "j": 9,
15
+ "k": 24,
16
+ "l": 20,
17
+ "m": 14,
18
+ "n": 1,
19
+ "o": 8,
20
+ "p": 27,
21
+ "q": 12,
22
+ "r": 22,
23
+ "s": 17,
24
+ "t": 25,
25
+ "u": 7,
26
+ "v": 21,
27
+ "w": 13,
28
+ "x": 19,
29
+ "y": 18,
30
+ "z": 11,
31
+ "|": 0,
32
+ "—": 28
33
+ }