MelanieKoe commited on
Commit
8d4ad5c
1 Parent(s): 8905bc7

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 63,
3
+ "<s>": 62
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
+ "60": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "61": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "62": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "63": {
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": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "%": 1,
3
+ "-": 2,
4
+ "0": 3,
5
+ "1": 4,
6
+ "2": 5,
7
+ "3": 6,
8
+ "4": 7,
9
+ "5": 8,
10
+ "6": 9,
11
+ "7": 10,
12
+ "9": 11,
13
+ "A": 12,
14
+ "B": 13,
15
+ "D": 14,
16
+ "E": 15,
17
+ "F": 16,
18
+ "G": 17,
19
+ "H": 18,
20
+ "J": 19,
21
+ "K": 20,
22
+ "L": 21,
23
+ "M": 22,
24
+ "N": 23,
25
+ "O": 24,
26
+ "P": 25,
27
+ "R": 26,
28
+ "S": 27,
29
+ "T": 28,
30
+ "V": 29,
31
+ "W": 30,
32
+ "Z": 31,
33
+ "[PAD]": 61,
34
+ "[UNK]": 60,
35
+ "a": 32,
36
+ "b": 33,
37
+ "c": 34,
38
+ "d": 35,
39
+ "e": 36,
40
+ "f": 37,
41
+ "g": 38,
42
+ "h": 39,
43
+ "i": 40,
44
+ "j": 41,
45
+ "k": 42,
46
+ "l": 43,
47
+ "m": 44,
48
+ "n": 45,
49
+ "o": 46,
50
+ "p": 47,
51
+ "r": 48,
52
+ "s": 49,
53
+ "t": 50,
54
+ "u": 51,
55
+ "v": 52,
56
+ "w": 53,
57
+ "x": 54,
58
+ "y": 55,
59
+ "z": 56,
60
+ "|": 0,
61
+ "ß": 57,
62
+ "ä": 58,
63
+ "ü": 59
64
+ }