Jethuestad commited on
Commit
403fdf4
1 Parent(s): 2c04a32

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 54,
3
+ "<s>": 53,
4
+ "[PAD]": 55
5
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "[PAD]",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": "<s>",
26
+ "eos_token": "</s>",
27
+ "pad_token": "[PAD]",
28
+ "unk_token": "[UNK]"
29
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "./",
6
+ "pad_token": "[PAD]",
7
+ "replace_word_delimiter_char": " ",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 1,
3
+ "1": 2,
4
+ "2": 3,
5
+ "3": 4,
6
+ "4": 5,
7
+ "5": 6,
8
+ "6": 7,
9
+ "7": 8,
10
+ "8": 9,
11
+ "9": 10,
12
+ "<": 11,
13
+ ">": 12,
14
+ "[PAD]": 54,
15
+ "[UNK]": 54,
16
+ "a": 13,
17
+ "b": 14,
18
+ "c": 15,
19
+ "d": 16,
20
+ "e": 17,
21
+ "f": 18,
22
+ "g": 19,
23
+ "h": 20,
24
+ "i": 21,
25
+ "j": 22,
26
+ "k": 23,
27
+ "l": 24,
28
+ "m": 25,
29
+ "n": 26,
30
+ "o": 27,
31
+ "p": 28,
32
+ "q": 29,
33
+ "r": 30,
34
+ "s": 31,
35
+ "t": 32,
36
+ "u": 33,
37
+ "v": 34,
38
+ "w": 35,
39
+ "x": 36,
40
+ "y": 37,
41
+ "z": 38,
42
+ "|": 0,
43
+ " ": 39,
44
+ "à": 40,
45
+ "ä": 41,
46
+ "å": 42,
47
+ "æ": 43,
48
+ "è": 44,
49
+ "é": 45,
50
+ "ò": 46,
51
+ "ó": 47,
52
+ "ô": 48,
53
+ "ö": 49,
54
+ "ø": 50,
55
+ "ü": 51
56
+ }