sanchit-gandhi HF staff commited on
Commit
4538f5e
1 Parent(s): 9df85a5

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 +48 -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": "adj",
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 45,
3
+ "'": 10,
4
+ "-": 26,
5
+ "a": 1,
6
+ "b": 12,
7
+ "c": 20,
8
+ "d": 22,
9
+ "e": 2,
10
+ "f": 24,
11
+ "g": 19,
12
+ "h": 32,
13
+ "i": 8,
14
+ "j": 23,
15
+ "k": 7,
16
+ "l": 6,
17
+ "m": 5,
18
+ "n": 4,
19
+ "o": 13,
20
+ "p": 25,
21
+ "r": 18,
22
+ "s": 11,
23
+ "t": 21,
24
+ "u": 17,
25
+ "v": 39,
26
+ "w": 15,
27
+ "y": 14,
28
+ "z": 43,
29
+ "|": 0,
30
+ "à": 37,
31
+ "á": 31,
32
+ "è": 42,
33
+ "é": 33,
34
+ "ê": 38,
35
+ "ì": 34,
36
+ "í": 29,
37
+ "ò": 35,
38
+ "ó": 27,
39
+ "ô": 44,
40
+ "ù": 40,
41
+ "ú": 36,
42
+ "ŋ": 9,
43
+ "ɔ": 16,
44
+ "ɛ": 3,
45
+ "̀": 30,
46
+ "́": 28,
47
+ "̂": 41
48
+ }