sanchit-gandhi commited on
Commit
17c0ff2
·
1 Parent(s): 6a4e73d

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