Jungwonchang commited on
Commit
49ef73d
1 Parent(s): 39d1267

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 72,
3
+ "<s>": 71
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "69": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "70": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "71": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "72": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": "eng",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eng": {
3
+ "%": 1,
4
+ "'": 2,
5
+ ",": 3,
6
+ "-": 4,
7
+ ".": 5,
8
+ "0": 6,
9
+ "1": 7,
10
+ "2": 8,
11
+ "3": 9,
12
+ "4": 10,
13
+ "5": 11,
14
+ "6": 12,
15
+ "7": 13,
16
+ "8": 14,
17
+ "9": 15,
18
+ "?": 16,
19
+ "A": 17,
20
+ "B": 18,
21
+ "C": 19,
22
+ "D": 20,
23
+ "E": 21,
24
+ "F": 22,
25
+ "G": 23,
26
+ "H": 24,
27
+ "I": 25,
28
+ "J": 26,
29
+ "K": 27,
30
+ "L": 28,
31
+ "M": 29,
32
+ "N": 30,
33
+ "O": 31,
34
+ "P": 32,
35
+ "Q": 33,
36
+ "R": 34,
37
+ "S": 35,
38
+ "T": 36,
39
+ "U": 37,
40
+ "V": 38,
41
+ "W": 39,
42
+ "X": 40,
43
+ "Y": 41,
44
+ "Z": 42,
45
+ "[PAD]": 70,
46
+ "[UNK]": 69,
47
+ "a": 43,
48
+ "b": 44,
49
+ "c": 45,
50
+ "d": 46,
51
+ "e": 47,
52
+ "f": 48,
53
+ "g": 49,
54
+ "h": 50,
55
+ "i": 51,
56
+ "j": 52,
57
+ "k": 53,
58
+ "l": 54,
59
+ "m": 55,
60
+ "n": 56,
61
+ "o": 57,
62
+ "p": 58,
63
+ "q": 59,
64
+ "r": 60,
65
+ "s": 61,
66
+ "t": 62,
67
+ "u": 63,
68
+ "v": 64,
69
+ "w": 65,
70
+ "x": 66,
71
+ "y": 67,
72
+ "z": 68,
73
+ "|": 0
74
+ }
75
+ }