sanchit-gandhi HF staff commited on
Commit
b0f94e8
1 Parent(s): 51f12d4

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": "kbp",
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
+ " ": 0,
3
+ "-": 6,
4
+ "_": 38,
5
+ "a": 32,
6
+ "b": 9,
7
+ "c": 16,
8
+ "d": 42,
9
+ "e": 12,
10
+ "f": 1,
11
+ "g": 18,
12
+ "h": 24,
13
+ "i": 7,
14
+ "j": 29,
15
+ "k": 13,
16
+ "l": 31,
17
+ "m": 14,
18
+ "n": 11,
19
+ "o": 27,
20
+ "p": 25,
21
+ "r": 35,
22
+ "s": 41,
23
+ "t": 5,
24
+ "u": 26,
25
+ "v": 23,
26
+ "w": 39,
27
+ "y": 30,
28
+ "z": 4,
29
+ "á": 36,
30
+ "é": 3,
31
+ "ñ": 19,
32
+ "ó": 8,
33
+ "ú": 21,
34
+ "đ": 20,
35
+ "ń": 28,
36
+ "ŋ": 40,
37
+ "ɔ": 34,
38
+ "ɖ": 2,
39
+ "ɛ": 10,
40
+ "ɣ": 33,
41
+ "ɩ": 37,
42
+ "ʋ": 22,
43
+ "́": 17,
44
+ "ḿ": 15
45
+ }