sanchit-gandhi HF staff commited on
Commit
86f59dd
1 Parent(s): 9dbc05a

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 +34 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "d",
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": "moa",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "d",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 26,
3
+ "'": 14,
4
+ "-": 16,
5
+ "_": 3,
6
+ "a": 2,
7
+ "b": 19,
8
+ "c": 8,
9
+ "d": 0,
10
+ "e": 23,
11
+ "f": 20,
12
+ "g": 13,
13
+ "h": 11,
14
+ "i": 17,
15
+ "j": 27,
16
+ "k": 21,
17
+ "l": 31,
18
+ "m": 24,
19
+ "n": 12,
20
+ "o": 6,
21
+ "p": 29,
22
+ "q": 7,
23
+ "r": 30,
24
+ "s": 22,
25
+ "t": 18,
26
+ "u": 5,
27
+ "v": 4,
28
+ "w": 9,
29
+ "y": 28,
30
+ "z": 10,
31
+ "ŋ": 25,
32
+ "ɔ": 15,
33
+ "ɛ": 1
34
+ }