MarOsz commited on
Commit
d0fdd64
1 Parent(s): 3e3a584

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 77,
3
+ "<s>": 76
4
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "74": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "75": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "76": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "77": {
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
+ "processor_class": "Wav2Vec2Processor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "[UNK]",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 9,
3
+ ",": 8,
4
+ ".": 28,
5
+ "?": 18,
6
+ "A": 35,
7
+ "B": 62,
8
+ "C": 26,
9
+ "D": 54,
10
+ "E": 40,
11
+ "F": 46,
12
+ "G": 59,
13
+ "H": 16,
14
+ "I": 57,
15
+ "J": 66,
16
+ "K": 37,
17
+ "L": 65,
18
+ "M": 58,
19
+ "N": 45,
20
+ "O": 6,
21
+ "P": 42,
22
+ "Q": 20,
23
+ "R": 32,
24
+ "S": 4,
25
+ "T": 70,
26
+ "U": 64,
27
+ "V": 11,
28
+ "W": 51,
29
+ "X": 27,
30
+ "Y": 72,
31
+ "Z": 7,
32
+ "[PAD]": 75,
33
+ "[UNK]": 74,
34
+ "a": 31,
35
+ "b": 33,
36
+ "c": 43,
37
+ "d": 44,
38
+ "e": 0,
39
+ "f": 2,
40
+ "g": 39,
41
+ "h": 41,
42
+ "i": 12,
43
+ "j": 14,
44
+ "k": 3,
45
+ "l": 52,
46
+ "m": 50,
47
+ "n": 21,
48
+ "o": 71,
49
+ "p": 5,
50
+ "q": 30,
51
+ "r": 13,
52
+ "s": 36,
53
+ "t": 53,
54
+ "u": 22,
55
+ "v": 19,
56
+ "w": 34,
57
+ "x": 10,
58
+ "y": 68,
59
+ "z": 67,
60
+ "|": 24,
61
+ "Ó": 61,
62
+ "ó": 48,
63
+ "ą": 15,
64
+ "Ć": 17,
65
+ "ć": 73,
66
+ "ę": 55,
67
+ "Ł": 47,
68
+ "ł": 69,
69
+ "ń": 60,
70
+ "Ő": 63,
71
+ "Ś": 38,
72
+ "ś": 25,
73
+ "Š": 49,
74
+ "Ź": 1,
75
+ "ź": 29,
76
+ "Ż": 23,
77
+ "ż": 56
78
+ }