Jatin-WIAI commited on
Commit
3fd0e0e
1 Parent(s): 7bdacef
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "ai4bharat/indicwav2vec_v1_gujarati",
6
+ "pad_token": "<pad>",
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "replace_word_delimiter_char": " ",
9
+ "special_tokens_map_file": "/home/users/jatin/.cache/huggingface/transformers/ac38963be5d6df686d9b5ae2904867017a613aa17b77d9323414ae3138f1c7fd.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "<unk>",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ ",": 9,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "|": 4,
8
+ "ઁ": 46,
9
+ "ં": 18,
10
+ "ઃ": 30,
11
+ "અ": 24,
12
+ "આ": 34,
13
+ "ઇ": 40,
14
+ "ઈ": 32,
15
+ "ઉ": 48,
16
+ "ઊ": 62,
17
+ "ઋ": 10,
18
+ "ઍ": 67,
19
+ "એ": 68,
20
+ "ઐ": 41,
21
+ "ઑ": 54,
22
+ "ઓ": 6,
23
+ "ઔ": 63,
24
+ "ક": 11,
25
+ "ખ": 69,
26
+ "ગ": 58,
27
+ "ઘ": 56,
28
+ "ઙ": 37,
29
+ "ચ": 27,
30
+ "છ": 43,
31
+ "જ": 28,
32
+ "ઝ": 52,
33
+ "ઞ": 25,
34
+ "ટ": 59,
35
+ "ઠ": 31,
36
+ "ડ": 33,
37
+ "ઢ": 42,
38
+ "ણ": 22,
39
+ "ત": 14,
40
+ "થ": 38,
41
+ "દ": 47,
42
+ "ધ": 64,
43
+ "ન": 5,
44
+ "પ": 60,
45
+ "ફ": 61,
46
+ "બ": 7,
47
+ "ભ": 39,
48
+ "મ": 15,
49
+ "ય": 17,
50
+ "ર": 19,
51
+ "લ": 65,
52
+ "ળ": 21,
53
+ "વ": 49,
54
+ "શ": 20,
55
+ "ષ": 36,
56
+ "સ": 13,
57
+ "હ": 23,
58
+ "ા": 45,
59
+ "િ": 44,
60
+ "ી": 12,
61
+ "ુ": 35,
62
+ "ૂ": 53,
63
+ "ૃ": 16,
64
+ "ૄ": 57,
65
+ "ૅ": 29,
66
+ "ે": 55,
67
+ "ૈ": 26,
68
+ "ૉ": 51,
69
+ "ો": 8,
70
+ "ૌ": 66,
71
+ "્": 50
72
+ }