sanchit-gandhi HF staff commited on
Commit
f55be18
1 Parent(s): a762fe4

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 +46 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "î",
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": "fra",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "î",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 29,
3
+ "'": 41,
4
+ "-": 2,
5
+ "_": 14,
6
+ "a": 19,
7
+ "b": 18,
8
+ "c": 10,
9
+ "d": 17,
10
+ "e": 15,
11
+ "f": 20,
12
+ "g": 11,
13
+ "h": 22,
14
+ "i": 16,
15
+ "j": 36,
16
+ "k": 25,
17
+ "l": 43,
18
+ "m": 42,
19
+ "n": 34,
20
+ "o": 35,
21
+ "p": 31,
22
+ "q": 9,
23
+ "r": 23,
24
+ "s": 26,
25
+ "t": 33,
26
+ "u": 4,
27
+ "v": 27,
28
+ "x": 8,
29
+ "y": 6,
30
+ "z": 1,
31
+ "à": 28,
32
+ "â": 38,
33
+ "ç": 39,
34
+ "è": 7,
35
+ "é": 24,
36
+ "ê": 13,
37
+ "ë": 32,
38
+ "î": 0,
39
+ "ï": 40,
40
+ "ô": 12,
41
+ "ù": 3,
42
+ "û": 5,
43
+ "ü": 37,
44
+ "œ": 21,
45
+ "–": 30
46
+ }