sanchit-gandhi HF staff commited on
Commit
04d28cd
1 Parent(s): 0954949

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 +61 -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": "bss",
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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 58,
3
+ "'": 56,
4
+ "-": 27,
5
+ "a": 9,
6
+ "b": 2,
7
+ "c": 28,
8
+ "d": 8,
9
+ "e": 5,
10
+ "f": 54,
11
+ "g": 17,
12
+ "h": 19,
13
+ "i": 30,
14
+ "j": 50,
15
+ "k": 15,
16
+ "l": 12,
17
+ "m": 6,
18
+ "n": 1,
19
+ "o": 22,
20
+ "p": 25,
21
+ "r": 41,
22
+ "s": 14,
23
+ "t": 16,
24
+ "u": 33,
25
+ "v": 57,
26
+ "w": 20,
27
+ "y": 11,
28
+ "z": 42,
29
+ "|": 0,
30
+ "á": 7,
31
+ "â": 35,
32
+ "é": 3,
33
+ "ê": 32,
34
+ "í": 26,
35
+ "î": 51,
36
+ "ó": 29,
37
+ "ô": 49,
38
+ "ú": 38,
39
+ "û": 53,
40
+ "ā": 45,
41
+ "ē": 31,
42
+ "ě": 37,
43
+ "ī": 47,
44
+ "ń": 43,
45
+ "ŋ": 21,
46
+ "ō": 48,
47
+ "ū": 52,
48
+ "ǎ": 44,
49
+ "ǐ": 46,
50
+ "ǒ": 34,
51
+ "ǔ": 55,
52
+ "ɔ": 13,
53
+ "ə": 18,
54
+ "ɛ": 4,
55
+ "ʼ": 23,
56
+ "́": 10,
57
+ "̂": 39,
58
+ "̄": 24,
59
+ "̌": 40,
60
+ "ḿ": 36
61
+ }