Hugging Face's logo

PolyChirag
/
Marathi_ASR_using_xlsr_wav2vec

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
PolyChirag commited on
Commit
c119041
•
1 Parent(s): 9f3af3e

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 +47 -0
  4. vocab.json +85 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 84,
3
+ "<s>": 83
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "81": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "82": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "83": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "84": {
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
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 61,
3
+ "[PAD]": 82,
4
+ "[UNK]": 81,
5
+ "|": 58,
6
+ "ँ": 35,
7
+ "ं": 43,
8
+ "ः": 27,
9
+ "अ": 40,
10
+ "आ": 32,
11
+ "इ": 2,
12
+ "ई": 67,
13
+ "उ": 15,
14
+ "ऊ": 7,
15
+ "ऋ": 55,
16
+ "ऌ": 71,
17
+ "ऍ": 19,
18
+ "ऎ": 20,
19
+ "ए": 28,
20
+ "ऐ": 45,
21
+ "ऑ": 41,
22
+ "ओ": 63,
23
+ "औ": 68,
24
+ "क": 56,
25
+ "ख": 51,
26
+ "ग": 18,
27
+ "घ": 29,
28
+ "ङ": 59,
29
+ "च": 48,
30
+ "छ": 66,
31
+ "ज": 12,
32
+ "झ": 49,
33
+ "ञ": 60,
34
+ "ट": 0,
35
+ "ठ": 26,
36
+ "ड": 75,
37
+ "ढ": 38,
38
+ "ण": 39,
39
+ "त": 42,
40
+ "थ": 36,
41
+ "द": 53,
42
+ "ध": 23,
43
+ "न": 9,
44
+ "प": 5,
45
+ "फ": 6,
46
+ "ब": 52,
47
+ "भ": 21,
48
+ "म": 24,
49
+ "य": 10,
50
+ "र": 72,
51
+ "ऱ": 54,
52
+ "ल": 8,
53
+ "ळ": 50,
54
+ "व": 62,
55
+ "श": 64,
56
+ "ष": 14,
57
+ "स": 47,
58
+ "ह": 78,
59
+ "़": 65,
60
+ "ऽ": 44,
61
+ "ा": 22,
62
+ "ि": 73,
63
+ "ी": 25,
64
+ "ु": 17,
65
+ "ू": 70,
66
+ "ृ": 16,
67
+ "ॄ": 13,
68
+ "ॅ": 30,
69
+ "ॆ": 80,
70
+ "े": 1,
71
+ "ै": 3,
72
+ "ॉ": 74,
73
+ "ॊ": 33,
74
+ "ो": 46,
75
+ "ौ": 57,
76
+ "्": 76,
77
+ "॓": 11,
78
+ "॔": 77,
79
+ "य़": 4,
80
+ "ॢ": 37,
81
+ "।": 31,
82
+ "॥": 79,
83
+ "ॲ": 69,
84
+ "’": 34
85
+ }