minjibi commited on
Commit
5b0d5a5
·
1 Parent(s): 62d28da

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 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "pad_token": "[PAD]",
6
+ "processor_class": "Wav2Vec2Processor",
7
+ "replace_word_delimiter_char": " ",
8
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
9
+ "unk_token": "[UNK]",
10
+ "word_delimiter_token": "|"
11
+ }
vocab.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 66,
3
+ "[UNK]": 65,
4
+ "|": 38,
5
+ "ก": 56,
6
+ "ข": 6,
7
+ "ค": 46,
8
+ "ฆ": 64,
9
+ "ง": 5,
10
+ "จ": 10,
11
+ "ฉ": 17,
12
+ "ช": 15,
13
+ "ซ": 39,
14
+ "ฌ": 7,
15
+ "ญ": 2,
16
+ "ฎ": 3,
17
+ "ฏ": 14,
18
+ "ฐ": 45,
19
+ "ฒ": 50,
20
+ "ณ": 41,
21
+ "ด": 20,
22
+ "ต": 62,
23
+ "ถ": 21,
24
+ "ท": 12,
25
+ "ธ": 22,
26
+ "น": 58,
27
+ "บ": 60,
28
+ "ป": 9,
29
+ "ผ": 34,
30
+ "ฝ": 36,
31
+ "พ": 32,
32
+ "ฟ": 43,
33
+ "ภ": 63,
34
+ "ม": 33,
35
+ "ย": 19,
36
+ "ร": 55,
37
+ "ฤ": 0,
38
+ "ล": 53,
39
+ "ว": 18,
40
+ "ศ": 47,
41
+ "ษ": 29,
42
+ "ส": 11,
43
+ "ห": 51,
44
+ "ฬ": 4,
45
+ "อ": 44,
46
+ "ฮ": 52,
47
+ "ะ": 23,
48
+ "ั": 42,
49
+ "า": 54,
50
+ "ำ": 61,
51
+ "ิ": 40,
52
+ "ี": 13,
53
+ "ึ": 1,
54
+ "ื": 57,
55
+ "ุ": 59,
56
+ "ู": 24,
57
+ "ฺ": 37,
58
+ "เ": 30,
59
+ "แ": 49,
60
+ "โ": 27,
61
+ "ใ": 35,
62
+ "ไ": 25,
63
+ "็": 8,
64
+ "่": 31,
65
+ "้": 16,
66
+ "๊": 28,
67
+ "๋": 48,
68
+ "์": 26
69
+ }