sanchit-gandhi HF staff commited on
Commit
841e683
1 Parent(s): 08c0d8c

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 +33 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "a",
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": "bcl",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "a",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 30,
3
+ "'": 27,
4
+ "-": 21,
5
+ "a": 0,
6
+ "b": 14,
7
+ "c": 22,
8
+ "d": 9,
9
+ "e": 18,
10
+ "f": 23,
11
+ "g": 4,
12
+ "h": 17,
13
+ "i": 3,
14
+ "j": 20,
15
+ "k": 7,
16
+ "l": 12,
17
+ "m": 8,
18
+ "n": 2,
19
+ "o": 5,
20
+ "p": 13,
21
+ "q": 28,
22
+ "r": 15,
23
+ "s": 6,
24
+ "t": 10,
25
+ "u": 11,
26
+ "v": 26,
27
+ "w": 19,
28
+ "x": 29,
29
+ "y": 16,
30
+ "z": 25,
31
+ "|": 1,
32
+ "—": 24
33
+ }