OmarElSayed commited on
Commit
c01e8ba
1 Parent(s): 2132c20

Upload processor

Browse files
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 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "my_model9/",
7
+ "pad_token": "<pad>",
8
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--jonatasgrosman--wav2vec2-large-xlsr-53-arabic/snapshots/af46c2d8531b8dcbb5e23b952f739b372c2e5d2d/special_tokens_map.json",
11
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
+ "unk_token": "<unk>",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "-": 5,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "|": 4,
8
+ "ء": 6,
9
+ "آ": 7,
10
+ "أ": 8,
11
+ "ؤ": 9,
12
+ "إ": 10,
13
+ "ئ": 11,
14
+ "ا": 12,
15
+ "ب": 13,
16
+ "ة": 14,
17
+ "ت": 15,
18
+ "ث": 16,
19
+ "ج": 17,
20
+ "ح": 18,
21
+ "خ": 19,
22
+ "د": 20,
23
+ "ذ": 21,
24
+ "ر": 22,
25
+ "ز": 23,
26
+ "س": 24,
27
+ "ش": 25,
28
+ "ص": 26,
29
+ "ض": 27,
30
+ "ط": 28,
31
+ "ظ": 29,
32
+ "ع": 30,
33
+ "غ": 31,
34
+ "ـ": 32,
35
+ "ف": 33,
36
+ "ق": 34,
37
+ "ك": 35,
38
+ "ل": 36,
39
+ "م": 37,
40
+ "ن": 38,
41
+ "ه": 39,
42
+ "و": 40,
43
+ "ى": 41,
44
+ "ي": 42,
45
+ "ً": 43,
46
+ "ٌ": 44,
47
+ "ٍ": 45,
48
+ "َ": 46,
49
+ "ُ": 47,
50
+ "ِ": 48,
51
+ "ّ": 49,
52
+ "ْ": 50
53
+ }