mostafaashahin commited on
Commit
2f31b91
1 Parent(s): 6ef522f

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": false,
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
+ "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
+ "target_lang": null,
11
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
+ "unk_token": "<unk>",
13
+ "word_delimiter_token": ""
14
+ }
vocab.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 0,
3
+ "<unk>": 1,
4
+ "aa": 32,
5
+ "ae": 22,
6
+ "ah": 23,
7
+ "aw": 24,
8
+ "ay": 12,
9
+ "b": 11,
10
+ "ch": 33,
11
+ "d": 4,
12
+ "dh": 6,
13
+ "eh": 34,
14
+ "er": 29,
15
+ "ey": 35,
16
+ "f": 38,
17
+ "g": 5,
18
+ "hh": 26,
19
+ "ih": 10,
20
+ "iy": 7,
21
+ "jh": 3,
22
+ "k": 2,
23
+ "l": 9,
24
+ "m": 17,
25
+ "n": 30,
26
+ "ng": 37,
27
+ "ow": 27,
28
+ "oy": 14,
29
+ "p": 19,
30
+ "r": 13,
31
+ "s": 20,
32
+ "sh": 21,
33
+ "t": 15,
34
+ "th": 28,
35
+ "uh": 36,
36
+ "uw": 39,
37
+ "v": 18,
38
+ "w": 25,
39
+ "y": 31,
40
+ "z": 8,
41
+ "zh": 16
42
+ }