sanchit-gandhi HF staff commited on
Commit
8f87b39
1 Parent(s): 6e6eb2c

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 +35 -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": "bex",
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 32,
3
+ "'": 13,
4
+ "2": 31,
5
+ "3": 29,
6
+ "8": 30,
7
+ "a": 1,
8
+ "b": 9,
9
+ "c": 27,
10
+ "d": 7,
11
+ "e": 5,
12
+ "g": 16,
13
+ "h": 28,
14
+ "i": 2,
15
+ "j": 25,
16
+ "k": 3,
17
+ "l": 14,
18
+ "m": 8,
19
+ "n": 6,
20
+ "o": 10,
21
+ "p": 23,
22
+ "r": 18,
23
+ "s": 24,
24
+ "t": 12,
25
+ "u": 20,
26
+ "w": 26,
27
+ "y": 15,
28
+ "z": 21,
29
+ "|": 0,
30
+ "ë": 19,
31
+ "ï": 11,
32
+ "ö": 17,
33
+ "ŋ": 22,
34
+ "ɔ": 4
35
+ }