sanchit-gandhi commited on
Commit
fe4b70c
·
1 Parent(s): 808dddd

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 +34 -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": "ake",
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 7,
3
+ "'": 17,
4
+ "-": 21,
5
+ "0": 9,
6
+ "1": 3,
7
+ "2": 31,
8
+ "3": 20,
9
+ "4": 27,
10
+ "5": 23,
11
+ "6": 24,
12
+ "7": 5,
13
+ "8": 13,
14
+ "9": 14,
15
+ "_": 10,
16
+ "a": 22,
17
+ "e": 26,
18
+ "i": 19,
19
+ "k": 4,
20
+ "m": 30,
21
+ "n": 12,
22
+ "o": 25,
23
+ "p": 11,
24
+ "r": 8,
25
+ "s": 18,
26
+ "t": 15,
27
+ "u": 16,
28
+ "w": 2,
29
+ "y": 1,
30
+ "ɨ": 6,
31
+ "ʉ": 28,
32
+ "–": 0,
33
+ "—": 29
34
+ }