aliyzd95 commited on
Commit
ab708ca
·
1 Parent(s): eb96d25

Upload processor

Browse files
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
 
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
 
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 +1,6 @@
 
 
 
 
 
 
 
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
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<pad>": 0,
4
+ "<s>": 1,
5
+ "<unk>": 3,
6
+ "|": 4,
7
+ "آ": 5,
8
+ "ئ": 6,
9
+ "ا": 7,
10
+ "ب": 8,
11
+ "ت": 9,
12
+ "ث": 10,
13
+ "ج": 11,
14
+ "ح": 12,
15
+ "خ": 13,
16
+ "د": 14,
17
+ "ذ": 15,
18
+ "ر": 16,
19
+ "ز": 17,
20
+ "س": 18,
21
+ "ش": 19,
22
+ "ص": 20,
23
+ "ض": 21,
24
+ "ط": 22,
25
+ "ظ": 23,
26
+ "ع": 24,
27
+ "غ": 25,
28
+ "ف": 26,
29
+ "ق": 27,
30
+ "ل": 28,
31
+ "م": 29,
32
+ "ن": 30,
33
+ "ه": 31,
34
+ "و": 32,
35
+ "پ": 33,
36
+ "چ": 34,
37
+ "ژ": 35,
38
+ "ک": 36,
39
+ "گ": 37,
40
+ "ی": 38,
41
+ "‌": 39
42
+ }