schalor commited on
Commit
348d9c4
·
verified ·
1 Parent(s): bfe52ac

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 70,
3
+ "<s>": 69
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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "__PAD__",
21
+ "unk_token": "__UNK__"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "./",
6
+ "pad_token": "__PAD__",
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "replace_word_delimiter_char": " ",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "__UNK__",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__PAD__": 0,
3
+ "__UNK__": 1,
4
+ "|": 2,
5
+ "ँ": 3,
6
+ "ं": 4,
7
+ "अ": 5,
8
+ "आ": 6,
9
+ "इ": 7,
10
+ "ई": 8,
11
+ "उ": 9,
12
+ "ऋ": 10,
13
+ "ए": 11,
14
+ "ऐ": 12,
15
+ "ओ": 13,
16
+ "औ": 14,
17
+ "क": 15,
18
+ "ख": 16,
19
+ "ग": 17,
20
+ "घ": 18,
21
+ "ङ": 19,
22
+ "च": 20,
23
+ "छ": 21,
24
+ "ज": 22,
25
+ "झ": 23,
26
+ "ञ": 24,
27
+ "ट": 25,
28
+ "ठ": 26,
29
+ "ड": 27,
30
+ "ढ": 28,
31
+ "ण": 29,
32
+ "त": 30,
33
+ "थ": 31,
34
+ "द": 32,
35
+ "ध": 33,
36
+ "न": 34,
37
+ "प": 35,
38
+ "फ": 36,
39
+ "ब": 37,
40
+ "भ": 38,
41
+ "म": 39,
42
+ "य": 40,
43
+ "र": 41,
44
+ "ल": 42,
45
+ "व": 43,
46
+ "श": 44,
47
+ "ष": 45,
48
+ "स": 46,
49
+ "ह": 47,
50
+ "ा": 48,
51
+ "ि": 49,
52
+ "ी": 50,
53
+ "ु": 51,
54
+ "ू": 52,
55
+ "ृ": 53,
56
+ "े": 54,
57
+ "ै": 55,
58
+ "ो": 56,
59
+ "ौ": 57,
60
+ "्": 58,
61
+ "०": 59,
62
+ "१": 60,
63
+ "२": 61,
64
+ "३": 62,
65
+ "४": 63,
66
+ "५": 64,
67
+ "६": 65,
68
+ "७": 66,
69
+ "८": 67,
70
+ "९": 68
71
+ }