tgrhn commited on
Commit
a4625d6
1 Parent(s): af381ef

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 52,
3
+ "<s>": 51
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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
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": "./",
7
+ "pad_token": "[PAD]",
8
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "special_tokens_map_file": null,
11
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
+ "unk_token": "[UNK]",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\n": 0,
3
+ "+": 2,
4
+ "/": 3,
5
+ "0": 4,
6
+ "1": 5,
7
+ "2": 6,
8
+ "3": 7,
9
+ "4": 8,
10
+ "5": 9,
11
+ "6": 10,
12
+ "8": 11,
13
+ "[PAD]": 50,
14
+ "[UNK]": 49,
15
+ "\\": 12,
16
+ "_": 13,
17
+ "a": 14,
18
+ "b": 15,
19
+ "c": 16,
20
+ "d": 17,
21
+ "e": 18,
22
+ "f": 19,
23
+ "g": 20,
24
+ "h": 21,
25
+ "i": 22,
26
+ "j": 23,
27
+ "k": 24,
28
+ "l": 25,
29
+ "m": 26,
30
+ "n": 27,
31
+ "o": 28,
32
+ "p": 29,
33
+ "q": 30,
34
+ "r": 31,
35
+ "s": 32,
36
+ "t": 33,
37
+ "u": 34,
38
+ "v": 35,
39
+ "w": 36,
40
+ "x": 37,
41
+ "y": 38,
42
+ "z": 39,
43
+ "|": 1,
44
+ "ç": 40,
45
+ "é": 41,
46
+ "ö": 42,
47
+ "ü": 43,
48
+ "ğ": 44,
49
+ "ı": 45,
50
+ "ş": 46,
51
+ "̇": 47,
52
+ "…": 48
53
+ }