navaaesarosh commited on
Commit
8b5ef6e
1 Parent(s): b27d64b

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 56,
3
+ "<s>": 55
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": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<s>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ ],
32
+ "bos_token": "<s>",
33
+ "eos_token": "</s>",
34
+ "pad_token": "[PAD]",
35
+ "unk_token": "[UNK]"
36
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 54,
3
+ "[UNK]": 53,
4
+ "|": 0,
5
+ "ء": 1,
6
+ "آ": 2,
7
+ "أ": 3,
8
+ "ؤ": 4,
9
+ "ئ": 5,
10
+ "ا": 6,
11
+ "ب": 7,
12
+ "ت": 8,
13
+ "ث": 9,
14
+ "ج": 10,
15
+ "ح": 11,
16
+ "خ": 12,
17
+ "د": 13,
18
+ "ذ": 14,
19
+ "ر": 15,
20
+ "ز": 16,
21
+ "س": 17,
22
+ "ش": 18,
23
+ "ص": 19,
24
+ "ض": 20,
25
+ "ط": 21,
26
+ "ظ": 22,
27
+ "ع": 23,
28
+ "غ": 24,
29
+ "ف": 25,
30
+ "ق": 26,
31
+ "ك": 27,
32
+ "ل": 28,
33
+ "م": 29,
34
+ "ن": 30,
35
+ "ه": 31,
36
+ "و": 32,
37
+ "ى": 33,
38
+ "ي": 34,
39
+ "ٹ": 35,
40
+ "پ": 36,
41
+ "چ": 37,
42
+ "ڈ": 38,
43
+ "ڑ": 39,
44
+ "ژ": 40,
45
+ "ک": 41,
46
+ "گ": 42,
47
+ "ں": 43,
48
+ "ھ": 44,
49
+ "ہ": 45,
50
+ "ۂ": 46,
51
+ "ۃ": 47,
52
+ "ی": 48,
53
+ "ے": 49,
54
+ "ۓ": 50,
55
+ "ﷲ": 51,
56
+ "ﷺ": 52
57
+ }