sanchit-gandhi HF staff commited on
Commit
d458b22
1 Parent(s): 22980f3

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 +32 -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": "maw",
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 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 29,
3
+ "'": 24,
4
+ "-": 19,
5
+ "a": 1,
6
+ "b": 7,
7
+ "d": 11,
8
+ "e": 15,
9
+ "f": 26,
10
+ "g": 18,
11
+ "h": 25,
12
+ "i": 2,
13
+ "k": 10,
14
+ "l": 9,
15
+ "m": 5,
16
+ "n": 3,
17
+ "o": 20,
18
+ "p": 22,
19
+ "r": 14,
20
+ "s": 8,
21
+ "t": 13,
22
+ "u": 4,
23
+ "v": 27,
24
+ "w": 23,
25
+ "y": 6,
26
+ "z": 21,
27
+ "|": 0,
28
+ "ŋ": 12,
29
+ "ɛ": 17,
30
+ "ԑ": 28,
31
+ "ↄ": 16
32
+ }