sanchit-gandhi HF staff commited on
Commit
76786c8
1 Parent(s): 83bfd57

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 +55 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ɔ",
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": "abi",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ɔ",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 3,
3
+ "'": 20,
4
+ "-": 45,
5
+ "_": 47,
6
+ "a": 52,
7
+ "b": 13,
8
+ "c": 39,
9
+ "d": 36,
10
+ "e": 30,
11
+ "f": 22,
12
+ "g": 49,
13
+ "h": 5,
14
+ "i": 7,
15
+ "j": 43,
16
+ "k": 9,
17
+ "l": 44,
18
+ "m": 27,
19
+ "n": 33,
20
+ "o": 35,
21
+ "p": 14,
22
+ "r": 48,
23
+ "s": 25,
24
+ "t": 46,
25
+ "u": 17,
26
+ "w": 19,
27
+ "y": 24,
28
+ "á": 10,
29
+ "â": 37,
30
+ "é": 41,
31
+ "ê": 1,
32
+ "í": 15,
33
+ "î": 26,
34
+ "ó": 23,
35
+ "ô": 38,
36
+ "ú": 34,
37
+ "û": 51,
38
+ "ě": 6,
39
+ "ń": 18,
40
+ "ǎ": 40,
41
+ "ǐ": 12,
42
+ "ǒ": 2,
43
+ "ǔ": 16,
44
+ "ɔ": 0,
45
+ "ɛ": 28,
46
+ "ɩ": 8,
47
+ "ʋ": 31,
48
+ "́": 42,
49
+ "̂": 4,
50
+ "̌": 11,
51
+ "έ": 29,
52
+ "ί": 21,
53
+ "ε": 50,
54
+ "ḿ": 32
55
+ }