Hugging Face's logo

vedamaganti
/
wav2vec2-xls-r-300m-hindi-colab

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Model card Files Community
vedamaganti commited on
Commit
d08df99
·
verified ·
1 Parent(s): aa4aa64

Upload processor

Browse files
Files changed (5) hide show
  1. added_tokens.json +4 -0
  2. preprocessor_config.json +10 -0
  3. special_tokens_map.json +6 -0
  4. tokenizer_config.json +48 -0
  5. vocab.json +99 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 98,
3
+ "<s>": 97
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 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "95": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "96": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "97": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "98": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "processor_class": "Wav2Vec2Processor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "[UNK]",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "&": 1,
3
+ "[PAD]": 96,
4
+ "[UNK]": 95,
5
+ "a": 2,
6
+ "b": 3,
7
+ "c": 4,
8
+ "d": 5,
9
+ "e": 6,
10
+ "f": 7,
11
+ "g": 8,
12
+ "h": 9,
13
+ "i": 10,
14
+ "j": 11,
15
+ "k": 12,
16
+ "l": 13,
17
+ "m": 14,
18
+ "n": 15,
19
+ "o": 16,
20
+ "p": 17,
21
+ "q": 18,
22
+ "r": 19,
23
+ "s": 20,
24
+ "t": 21,
25
+ "u": 22,
26
+ "v": 23,
27
+ "w": 24,
28
+ "x": 25,
29
+ "y": 26,
30
+ "z": 27,
31
+ "|": 0,
32
+ "ँ": 28,
33
+ "ं": 29,
34
+ "ः": 30,
35
+ "अ": 31,
36
+ "आ": 32,
37
+ "इ": 33,
38
+ "ई": 34,
39
+ "उ": 35,
40
+ "ऊ": 36,
41
+ "ऋ": 37,
42
+ "ए": 38,
43
+ "ऐ": 39,
44
+ "ऑ": 40,
45
+ "ओ": 41,
46
+ "औ": 42,
47
+ "क": 43,
48
+ "ख": 44,
49
+ "ग": 45,
50
+ "घ": 46,
51
+ "च": 47,
52
+ "छ": 48,
53
+ "ज": 49,
54
+ "झ": 50,
55
+ "ञ": 51,
56
+ "ट": 52,
57
+ "ठ": 53,
58
+ "ड": 54,
59
+ "ढ": 55,
60
+ "ण": 56,
61
+ "त": 57,
62
+ "थ": 58,
63
+ "द": 59,
64
+ "ध": 60,
65
+ "न": 61,
66
+ "प": 62,
67
+ "फ": 63,
68
+ "ब": 64,
69
+ "भ": 65,
70
+ "म": 66,
71
+ "य": 67,
72
+ "र": 68,
73
+ "ल": 69,
74
+ "व": 70,
75
+ "श": 71,
76
+ "ष": 72,
77
+ "स": 73,
78
+ "ह": 74,
79
+ "़": 75,
80
+ "ा": 76,
81
+ "ि": 77,
82
+ "ी": 78,
83
+ "ु": 79,
84
+ "ू": 80,
85
+ "ृ": 81,
86
+ "ॅ": 82,
87
+ "े": 83,
88
+ "ै": 84,
89
+ "ॉ": 85,
90
+ "ो": 86,
91
+ "ौ": 87,
92
+ "्": 88,
93
+ "ज़": 89,
94
+ "ड़": 90,
95
+ "ढ़": 91,
96
+ "फ़": 92,
97
+ "–": 93,
98
+ "’": 94
99
+ }