alaleye commited on
Commit
6650450
1 Parent(s): 9b75926

Upload 4 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 61,
3
+ "<s>": 60
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "58": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "59": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "60": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "61": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "config": null,
39
+ "do_lower_case": false,
40
+ "eos_token": "</s>",
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "tokenizer_type": "wav2vec2-bert",
47
+ "unk_token": "[UNK]",
48
+ "word_delimiter_token": "|"
49
+ }
vocab.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 1,
3
+ "2": 2,
4
+ "[PAD]": 59,
5
+ "[UNK]": 58,
6
+ "a": 3,
7
+ "b": 4,
8
+ "c": 5,
9
+ "d": 6,
10
+ "e": 7,
11
+ "f": 8,
12
+ "g": 9,
13
+ "h": 10,
14
+ "i": 11,
15
+ "j": 12,
16
+ "k": 13,
17
+ "l": 14,
18
+ "m": 15,
19
+ "n": 16,
20
+ "o": 17,
21
+ "p": 18,
22
+ "r": 19,
23
+ "s": 20,
24
+ "t": 21,
25
+ "u": 22,
26
+ "v": 23,
27
+ "w": 24,
28
+ "x": 25,
29
+ "y": 26,
30
+ "z": 27,
31
+ "|": 0,
32
+ " ": 28,
33
+ "à": 29,
34
+ "á": 30,
35
+ "è": 31,
36
+ "é": 32,
37
+ "ì": 33,
38
+ "í": 34,
39
+ "ò": 35,
40
+ "ó": 36,
41
+ "ù": 37,
42
+ "ú": 38,
43
+ "ĕ": 39,
44
+ "ĭ": 40,
45
+ "ŏ": 41,
46
+ "ŭ": 42,
47
+ "ɑ": 43,
48
+ "ɔ": 44,
49
+ "ɖ": 45,
50
+ "ɛ": 46,
51
+ "ɩ": 47,
52
+ "̀": 48,
53
+ "́": 49,
54
+ "̂": 50,
55
+ "̆": 51,
56
+ "̌": 52,
57
+ "έ": 53,
58
+ "ε": 54,
59
+ "ὲ": 55,
60
+ "‘": 56,
61
+ "’": 57
62
+ }