minjibi commited on
Commit
ba147da
·
1 Parent(s): bd882de

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 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ ".": 49,
3
+ "[PAD]": 67,
4
+ "[UNK]": 66,
5
+ "|": 14,
6
+ "ก": 19,
7
+ "ข": 28,
8
+ "ค": 8,
9
+ "ฆ": 29,
10
+ "ง": 53,
11
+ "จ": 1,
12
+ "ฉ": 61,
13
+ "ช": 45,
14
+ "ซ": 20,
15
+ "ฌ": 18,
16
+ "ญ": 51,
17
+ "ฎ": 63,
18
+ "ฐ": 2,
19
+ "ฑ": 5,
20
+ "ฒ": 42,
21
+ "ณ": 52,
22
+ "ด": 46,
23
+ "ต": 44,
24
+ "ถ": 39,
25
+ "ท": 11,
26
+ "ธ": 34,
27
+ "น": 35,
28
+ "บ": 12,
29
+ "ป": 6,
30
+ "ผ": 59,
31
+ "ฝ": 33,
32
+ "พ": 7,
33
+ "ฟ": 32,
34
+ "ภ": 27,
35
+ "ม": 23,
36
+ "ย": 16,
37
+ "ร": 47,
38
+ "ฤ": 54,
39
+ "ล": 25,
40
+ "ว": 0,
41
+ "ศ": 21,
42
+ "ษ": 40,
43
+ "ส": 36,
44
+ "ห": 43,
45
+ "ฬ": 30,
46
+ "อ": 13,
47
+ "ฮ": 64,
48
+ "ะ": 10,
49
+ "ั": 26,
50
+ "า": 57,
51
+ "ำ": 41,
52
+ "ิ": 31,
53
+ "ี": 17,
54
+ "ึ": 3,
55
+ "ื": 56,
56
+ "ุ": 65,
57
+ "ู": 58,
58
+ "ฺ": 48,
59
+ "เ": 55,
60
+ "แ": 9,
61
+ "โ": 50,
62
+ "ใ": 37,
63
+ "ไ": 38,
64
+ "็": 62,
65
+ "่": 22,
66
+ "้": 24,
67
+ "๊": 15,
68
+ "๋": 60,
69
+ "์": 4
70
+ }