sanchit-gandhi HF staff commited on
Commit
cf247b4
1 Parent(s): b028172

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 +45 -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": "quc-dialect_east",
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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 42,
3
+ "'": 6,
4
+ "-": 29,
5
+ "0": 32,
6
+ "1": 31,
7
+ "2": 33,
8
+ "3": 39,
9
+ "4": 35,
10
+ "5": 38,
11
+ "6": 34,
12
+ "7": 36,
13
+ "8": 40,
14
+ "a": 1,
15
+ "b": 17,
16
+ "c": 10,
17
+ "d": 24,
18
+ "e": 5,
19
+ "f": 26,
20
+ "g": 25,
21
+ "h": 9,
22
+ "i": 2,
23
+ "j": 8,
24
+ "k": 4,
25
+ "l": 13,
26
+ "m": 19,
27
+ "n": 11,
28
+ "o": 14,
29
+ "p": 21,
30
+ "q": 15,
31
+ "r": 3,
32
+ "s": 20,
33
+ "t": 12,
34
+ "u": 7,
35
+ "v": 28,
36
+ "w": 16,
37
+ "x": 18,
38
+ "y": 22,
39
+ "z": 23,
40
+ "|": 0,
41
+ "ä": 30,
42
+ "ñ": 37,
43
+ "–": 27,
44
+ "—": 41
45
+ }