sanchit-gandhi HF staff commited on
Commit
bae8410
1 Parent(s): dcb27c9

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 +54 -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": "mnf",
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 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 51,
3
+ "'": 49,
4
+ "-": 50,
5
+ "a": 1,
6
+ "b": 2,
7
+ "c": 45,
8
+ "d": 25,
9
+ "e": 6,
10
+ "f": 28,
11
+ "g": 19,
12
+ "h": 23,
13
+ "i": 20,
14
+ "j": 37,
15
+ "k": 14,
16
+ "l": 12,
17
+ "m": 7,
18
+ "n": 3,
19
+ "o": 29,
20
+ "p": 34,
21
+ "s": 17,
22
+ "t": 5,
23
+ "u": 15,
24
+ "v": 39,
25
+ "w": 16,
26
+ "y": 22,
27
+ "z": 30,
28
+ "|": 0,
29
+ "à": 4,
30
+ "â": 40,
31
+ "è": 10,
32
+ "ê": 27,
33
+ "ì": 31,
34
+ "î": 47,
35
+ "ò": 21,
36
+ "ô": 48,
37
+ "ù": 32,
38
+ "û": 38,
39
+ "ě": 42,
40
+ "ŋ": 24,
41
+ "ǎ": 35,
42
+ "ǐ": 46,
43
+ "ǒ": 44,
44
+ "ǔ": 43,
45
+ "ȩ": 36,
46
+ "ɔ": 9,
47
+ "ə": 26,
48
+ "ɨ": 8,
49
+ "ˈ": 18,
50
+ "̀": 13,
51
+ "̂": 33,
52
+ "̌": 41,
53
+ "̧": 11
54
+ }