sanchit-gandhi HF staff commited on
Commit
4a54f9b
1 Parent(s): 72b65f4

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 +36 -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": "mor",
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 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 33,
3
+ "'": 32,
4
+ "-": 30,
5
+ "a": 1,
6
+ "b": 20,
7
+ "c": 23,
8
+ "d": 18,
9
+ "e": 5,
10
+ "f": 25,
11
+ "g": 10,
12
+ "i": 2,
13
+ "j": 28,
14
+ "k": 26,
15
+ "l": 7,
16
+ "m": 14,
17
+ "n": 3,
18
+ "o": 12,
19
+ "p": 27,
20
+ "r": 8,
21
+ "s": 21,
22
+ "t": 24,
23
+ "u": 13,
24
+ "v": 31,
25
+ "w": 16,
26
+ "y": 22,
27
+ "|": 0,
28
+ "ë": 19,
29
+ "ñ": 17,
30
+ "đ": 9,
31
+ "ŋ": 6,
32
+ "ǝ": 4,
33
+ "ɽ": 15,
34
+ "ḏ": 29,
35
+ "ṯ": 11
36
+ }