sanchit-gandhi HF staff commited on
Commit
6554d1e
1 Parent(s): 1dd9693

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": "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": "agg",
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 32,
3
+ "-": 23,
4
+ "0": 24,
5
+ "1": 25,
6
+ "2": 27,
7
+ "3": 31,
8
+ "4": 28,
9
+ "5": 29,
10
+ "6": 30,
11
+ "7": 26,
12
+ "a": 0,
13
+ "b": 11,
14
+ "d": 9,
15
+ "e": 12,
16
+ "f": 16,
17
+ "g": 17,
18
+ "h": 6,
19
+ "i": 10,
20
+ "k": 19,
21
+ "m": 5,
22
+ "n": 4,
23
+ "o": 3,
24
+ "p": 21,
25
+ "r": 7,
26
+ "s": 13,
27
+ "t": 22,
28
+ "u": 8,
29
+ "w": 20,
30
+ "y": 15,
31
+ "|": 1,
32
+ "ü": 14,
33
+ "ŋ": 18,
34
+ "ɨ": 2
35
+ }