sanchit-gandhi HF staff commited on
Commit
378a112
1 Parent(s): 57e572a

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