vitthalbhandari commited on
Commit
6952279
·
verified ·
1 Parent(s): 56bde76

Upload processor

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. processor_config.json +12 -0
  3. tokenizer_config.json +62 -0
  4. vocab.json +51 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 48,
3
+ "<s>": 47
4
+ }
processor_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "do_normalize": true,
4
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
5
+ "feature_size": 1,
6
+ "padding_side": "right",
7
+ "padding_value": 0.0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ },
11
+ "processor_class": "Wav2Vec2Processor"
12
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "45": {
12
+ "content": "[UNK]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "46": {
20
+ "content": "[PAD]",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "47": {
28
+ "content": "<s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "48": {
36
+ "content": "</s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": null,
45
+ "backend": "custom",
46
+ "bos_token": "<s>",
47
+ "do_lower_case": false,
48
+ "eos_token": "</s>",
49
+ "extra_special_tokens": [],
50
+ "is_local": true,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "model_specific_special_tokens": {
53
+ "word_delimiter_token": "|"
54
+ },
55
+ "pad_token": "[PAD]",
56
+ "processor_class": "Wav2Vec2Processor",
57
+ "replace_word_delimiter_char": " ",
58
+ "target_lang": "bxk",
59
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
60
+ "unk_token": "[UNK]",
61
+ "word_delimiter_token": "|"
62
+ }
vocab.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bxk": {
3
+ "-": 1,
4
+ "1": 2,
5
+ "9": 3,
6
+ "A": 4,
7
+ "B": 5,
8
+ "C": 6,
9
+ "E": 7,
10
+ "F": 8,
11
+ "G": 9,
12
+ "I": 10,
13
+ "K": 11,
14
+ "L": 12,
15
+ "M": 13,
16
+ "N": 14,
17
+ "O": 15,
18
+ "S": 16,
19
+ "T": 17,
20
+ "U": 18,
21
+ "Y": 19,
22
+ "[PAD]": 46,
23
+ "[UNK]": 45,
24
+ "a": 20,
25
+ "b": 21,
26
+ "c": 22,
27
+ "d": 23,
28
+ "e": 24,
29
+ "f": 25,
30
+ "g": 26,
31
+ "h": 27,
32
+ "i": 28,
33
+ "j": 29,
34
+ "k": 30,
35
+ "l": 31,
36
+ "m": 32,
37
+ "n": 33,
38
+ "o": 34,
39
+ "p": 35,
40
+ "r": 36,
41
+ "s": 37,
42
+ "t": 38,
43
+ "u": 39,
44
+ "v": 40,
45
+ "w": 41,
46
+ "x": 42,
47
+ "y": 43,
48
+ "z": 44,
49
+ "|": 0
50
+ }
51
+ }