Dmitriy commited on
Commit
78397ea
·
1 Parent(s): 740e4f4

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,
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "target_lang": null,
11
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
+ "unk_token": "<unk>",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "3": 5,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "F": 17,
8
+ "e": 32,
9
+ "i": 65,
10
+ "l": 76,
11
+ "|": 62,
12
+ "ঁ": 86,
13
+ "ং": 26,
14
+ "ঃ": 29,
15
+ "অ": 18,
16
+ "আ": 48,
17
+ "ই": 4,
18
+ "ঈ": 42,
19
+ "উ": 14,
20
+ "ঊ": 40,
21
+ "ঋ": 43,
22
+ "এ": 46,
23
+ "ঐ": 52,
24
+ "ও": 19,
25
+ "ঔ": 67,
26
+ "ক": 79,
27
+ "খ": 21,
28
+ "গ": 28,
29
+ "ঘ": 72,
30
+ "ঙ": 70,
31
+ "চ": 37,
32
+ "ছ": 49,
33
+ "জ": 78,
34
+ "ঝ": 75,
35
+ "ঞ": 16,
36
+ "ট": 20,
37
+ "ঠ": 44,
38
+ "ড": 55,
39
+ "ঢ": 85,
40
+ "ণ": 57,
41
+ "ত": 45,
42
+ "থ": 31,
43
+ "দ": 73,
44
+ "ধ": 13,
45
+ "ন": 80,
46
+ "প": 53,
47
+ "ফ": 58,
48
+ "ব": 51,
49
+ "ভ": 68,
50
+ "ম": 25,
51
+ "য": 81,
52
+ "র": 83,
53
+ "ল": 8,
54
+ "শ": 38,
55
+ "ষ": 34,
56
+ "স": 23,
57
+ "হ": 6,
58
+ "়": 36,
59
+ "া": 15,
60
+ "ি": 33,
61
+ "ী": 54,
62
+ "ু": 59,
63
+ "ূ": 50,
64
+ "ৃ": 60,
65
+ "ে": 82,
66
+ "ৈ": 10,
67
+ "ো": 11,
68
+ "ৌ": 27,
69
+ "্": 9,
70
+ "ৎ": 71,
71
+ "ৗ": 39,
72
+ "ড়": 22,
73
+ "য়": 77,
74
+ "০": 24,
75
+ "১": 61,
76
+ "২": 74,
77
+ "৩": 84,
78
+ "৪": 12,
79
+ "৫": 47,
80
+ "৬": 41,
81
+ "৭": 56,
82
+ "৮": 63,
83
+ "৯": 35,
84
+ "ৰ": 66,
85
+ "‌": 30,
86
+ "‍": 64,
87
+ "‎": 69,
88
+ "…": 7
89
+ }