sanchit-gandhi HF staff commited on
Commit
543241a
1 Parent(s): 2ade054

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