sanchit-gandhi HF staff commited on
Commit
427eb0f
1 Parent(s): 3b68dc3

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": "|",
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": "cla",
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 31,
3
+ "'": 21,
4
+ "-": 28,
5
+ "0": 30,
6
+ "2": 29,
7
+ "a": 1,
8
+ "b": 22,
9
+ "c": 24,
10
+ "d": 19,
11
+ "e": 8,
12
+ "f": 15,
13
+ "g": 16,
14
+ "h": 10,
15
+ "i": 2,
16
+ "j": 25,
17
+ "k": 9,
18
+ "l": 12,
19
+ "m": 3,
20
+ "n": 5,
21
+ "o": 14,
22
+ "p": 23,
23
+ "r": 17,
24
+ "s": 4,
25
+ "t": 6,
26
+ "u": 7,
27
+ "v": 27,
28
+ "w": 11,
29
+ "y": 13,
30
+ "z": 26,
31
+ "|": 0,
32
+ "ɓ": 18,
33
+ "ɗ": 20
34
+ }