Hugging Face's logo

Hemantrao
/
wav2vec2-large-xls-r-300m-hindi_marathi-code-switching-experimentx1

Automatic Speech Recognition
Transformers
Safetensors
Hindi
Marathi
wav2vec2
code-switching
ASR
multilingual
Eval Results
Model card Files
xet
Community
Hemantrao commited on
Commit
8e66fef
·
verified ·
1 Parent(s): 2fee0c3

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +48 -0
  4. vocab.json +106 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 105,
3
+ "<s>": 104
4
+ }
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
+ "102": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "103": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "104": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "105": {
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 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 0,
3
+ "!": 1,
4
+ "\"": 2,
5
+ "&": 3,
6
+ "'": 4,
7
+ ",": 5,
8
+ "-": 6,
9
+ ".": 7,
10
+ ":": 8,
11
+ ";": 9,
12
+ "?": 10,
13
+ "[PAD]": 103,
14
+ "[UNK]": 102,
15
+ "|": 11,
16
+ "ँ": 12,
17
+ "ं": 13,
18
+ "ः": 14,
19
+ "अ": 15,
20
+ "आ": 16,
21
+ "इ": 17,
22
+ "ई": 18,
23
+ "उ": 19,
24
+ "ऊ": 20,
25
+ "ऋ": 21,
26
+ "ऌ": 22,
27
+ "ऍ": 23,
28
+ "ऎ": 24,
29
+ "ए": 25,
30
+ "ऐ": 26,
31
+ "ऑ": 27,
32
+ "ओ": 28,
33
+ "औ": 29,
34
+ "क": 30,
35
+ "ख": 31,
36
+ "ग": 32,
37
+ "घ": 33,
38
+ "ङ": 34,
39
+ "च": 35,
40
+ "छ": 36,
41
+ "ज": 37,
42
+ "झ": 38,
43
+ "ञ": 39,
44
+ "ट": 40,
45
+ "ठ": 41,
46
+ "ड": 42,
47
+ "ढ": 43,
48
+ "ण": 44,
49
+ "त": 45,
50
+ "थ": 46,
51
+ "द": 47,
52
+ "ध": 48,
53
+ "न": 49,
54
+ "प": 50,
55
+ "फ": 51,
56
+ "ब": 52,
57
+ "भ": 53,
58
+ "म": 54,
59
+ "य": 55,
60
+ "र": 56,
61
+ "ऱ": 57,
62
+ "ल": 58,
63
+ "ळ": 59,
64
+ "व": 60,
65
+ "श": 61,
66
+ "ष": 62,
67
+ "स": 63,
68
+ "ह": 64,
69
+ "़": 65,
70
+ "ऽ": 66,
71
+ "ा": 67,
72
+ "ि": 68,
73
+ "ी": 69,
74
+ "ु": 70,
75
+ "ू": 71,
76
+ "ृ": 72,
77
+ "ॄ": 73,
78
+ "ॅ": 74,
79
+ "ॆ": 75,
80
+ "े": 76,
81
+ "ै": 77,
82
+ "ॉ": 78,
83
+ "ॊ": 79,
84
+ "ो": 80,
85
+ "ौ": 81,
86
+ "्": 82,
87
+ "॓": 83,
88
+ "॔": 84,
89
+ "क़": 85,
90
+ "ख़": 86,
91
+ "ग़": 87,
92
+ "ज़": 88,
93
+ "ड़": 89,
94
+ "ढ़": 90,
95
+ "फ़": 91,
96
+ "य़": 92,
97
+ "ॢ": 93,
98
+ "।": 94,
99
+ "॥": 95,
100
+ "ॲ": 96,
101
+ "–": 97,
102
+ "‘": 98,
103
+ "’": 99,
104
+ "“": 100,
105
+ "”": 101
106
+ }