sanchit-gandhi HF staff commited on
Commit
f386660
1 Parent(s): f25a6bc

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