sanchit-gandhi commited on
Commit
818d99f
·
1 Parent(s): 034c522

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 +42 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "n",
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": "cym",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "n",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 11,
3
+ "'": 15,
4
+ "-": 13,
5
+ "_": 8,
6
+ "a": 17,
7
+ "b": 24,
8
+ "c": 32,
9
+ "d": 1,
10
+ "e": 23,
11
+ "f": 19,
12
+ "g": 16,
13
+ "h": 6,
14
+ "i": 29,
15
+ "j": 25,
16
+ "l": 31,
17
+ "m": 21,
18
+ "n": 0,
19
+ "o": 7,
20
+ "p": 27,
21
+ "r": 14,
22
+ "s": 9,
23
+ "t": 39,
24
+ "u": 12,
25
+ "w": 37,
26
+ "x": 4,
27
+ "y": 20,
28
+ "z": 26,
29
+ "á": 38,
30
+ "â": 22,
31
+ "ê": 36,
32
+ "ë": 35,
33
+ "î": 3,
34
+ "ï": 30,
35
+ "ó": 10,
36
+ "ô": 33,
37
+ "ö": 34,
38
+ "û": 28,
39
+ "ŵ": 18,
40
+ "ŷ": 2,
41
+ "—": 5
42
+ }