sanchit-gandhi HF staff commited on
Commit
b98eb07
1 Parent(s): ad9a134

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 +37 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ñ",
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": "bsc",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ñ",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 13,
3
+ "-": 6,
4
+ "_": 29,
5
+ "a": 10,
6
+ "b": 24,
7
+ "c": 11,
8
+ "d": 28,
9
+ "e": 9,
10
+ "f": 15,
11
+ "g": 25,
12
+ "h": 19,
13
+ "i": 32,
14
+ "j": 27,
15
+ "k": 23,
16
+ "l": 1,
17
+ "m": 20,
18
+ "n": 31,
19
+ "o": 12,
20
+ "p": 16,
21
+ "r": 30,
22
+ "s": 34,
23
+ "t": 21,
24
+ "u": 17,
25
+ "w": 7,
26
+ "x": 22,
27
+ "y": 26,
28
+ "ë": 5,
29
+ "ñ": 0,
30
+ "ŋ": 4,
31
+ "ŝ": 33,
32
+ "ƴ": 14,
33
+ "ɓ": 8,
34
+ "ɗ": 3,
35
+ "̃": 2,
36
+ "ỹ": 18
37
+ }