Sethisak commited on
Commit
3181150
ยท
verified ยท
1 Parent(s): 767f370

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 74,
3
+ "<s>": 73
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 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "71": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "72": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "73": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "74": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "target_lang": null,
46
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
47
+ "unk_token": "[UNK]",
48
+ "word_delimiter_token": "|"
49
+ }
vocab.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 72,
3
+ "[UNK]": 71,
4
+ "|": 35,
5
+ "แž€": 68,
6
+ "แž": 70,
7
+ "แž‚": 67,
8
+ "แžƒ": 58,
9
+ "แž„": 3,
10
+ "แž…": 38,
11
+ "แž†": 14,
12
+ "แž‡": 53,
13
+ "แžˆ": 4,
14
+ "แž‰": 49,
15
+ "แžŠ": 16,
16
+ "แž‹": 13,
17
+ "แžŒ": 22,
18
+ "แž": 9,
19
+ "แžŽ": 8,
20
+ "แž": 18,
21
+ "แž": 46,
22
+ "แž‘": 55,
23
+ "แž’": 59,
24
+ "แž“": 45,
25
+ "แž”": 34,
26
+ "แž•": 51,
27
+ "แž–": 23,
28
+ "แž—": 47,
29
+ "แž˜": 62,
30
+ "แž™": 37,
31
+ "แžš": 26,
32
+ "แž›": 17,
33
+ "แžœ": 1,
34
+ "แžŸ": 7,
35
+ "แž ": 25,
36
+ "แžก": 33,
37
+ "แžข": 60,
38
+ "แžฅ": 40,
39
+ "แžง": 11,
40
+ "แžช": 21,
41
+ "แžซ": 66,
42
+ "แžฌ": 41,
43
+ "แžญ": 31,
44
+ "แžฎ": 24,
45
+ "แžฏ": 48,
46
+ "แžฑ": 10,
47
+ "แžถ": 69,
48
+ "แžท": 0,
49
+ "แžธ": 50,
50
+ "แžน": 65,
51
+ "แžบ": 52,
52
+ "แžป": 19,
53
+ "แžผ": 64,
54
+ "แžฝ": 44,
55
+ "แžพ": 43,
56
+ "แžฟ": 63,
57
+ "แŸ€": 6,
58
+ "แŸ": 39,
59
+ "แŸ‚": 12,
60
+ "แŸƒ": 20,
61
+ "แŸ„": 30,
62
+ "แŸ…": 15,
63
+ "แŸ†": 42,
64
+ "แŸ‡": 2,
65
+ "แŸˆ": 27,
66
+ "แŸ‰": 61,
67
+ "แŸŠ": 5,
68
+ "แŸ‹": 54,
69
+ "แŸŒ": 36,
70
+ "แŸ": 32,
71
+ "แŸŽ": 29,
72
+ "แŸ": 57,
73
+ "แŸ": 28,
74
+ "แŸ’": 56
75
+ }