sanchit-gandhi HF staff commited on
Commit
ca94bdf
1 Parent(s): 092adda

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": "é",
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": "dgk",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "é",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 30,
3
+ "'": 28,
4
+ "-": 36,
5
+ "2": 33,
6
+ "_": 22,
7
+ "a": 1,
8
+ "b": 43,
9
+ "d": 8,
10
+ "e": 45,
11
+ "g": 6,
12
+ "h": 14,
13
+ "i": 32,
14
+ "j": 11,
15
+ "k": 34,
16
+ "l": 20,
17
+ "m": 12,
18
+ "n": 19,
19
+ "o": 39,
20
+ "p": 13,
21
+ "r": 7,
22
+ "s": 35,
23
+ "t": 10,
24
+ "u": 3,
25
+ "w": 24,
26
+ "y": 42,
27
+ "à": 38,
28
+ "á": 21,
29
+ "é": 0,
30
+ "ì": 16,
31
+ "í": 17,
32
+ "ò": 15,
33
+ "ó": 26,
34
+ "ù": 4,
35
+ "ú": 25,
36
+ "ŋ": 41,
37
+ "ɓ": 23,
38
+ "ɔ": 18,
39
+ "ɗ": 27,
40
+ "ə": 31,
41
+ "ɛ": 44,
42
+ "̀": 40,
43
+ "́": 29,
44
+ "̰": 9,
45
+ "ә": 2,
46
+ "ḭ": 5,
47
+ "ṵ": 37
48
+ }