Hugging Face's logo

auditi41
/
wav2vec2-large-xlsr-53-Bengali

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
auditi41 commited on
Commit
d98ca77
•
1 Parent(s): 1346adc

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +10 -0
  3. vocab.json +82 -0
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 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "pad_token": "[PAD]",
6
+ "replace_word_delimiter_char": " ",
7
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
8
+ "unk_token": "[UNK]",
9
+ "word_delimiter_token": "|"
10
+ }
vocab.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 54,
3
+ "/": 73,
4
+ "[PAD]": 79,
5
+ "[UNK]": 78,
6
+ "a": 12,
7
+ "e": 1,
8
+ "g": 55,
9
+ "l": 35,
10
+ "o": 0,
11
+ "p": 24,
12
+ "y": 14,
13
+ "|": 67,
14
+ "।": 53,
15
+ "॥": 56,
16
+ "ঁ": 74,
17
+ "ং": 65,
18
+ "ঃ": 34,
19
+ "অ": 6,
20
+ "আ": 23,
21
+ "ই": 58,
22
+ "ঈ": 18,
23
+ "উ": 26,
24
+ "ঊ": 16,
25
+ "ঋ": 49,
26
+ "এ": 39,
27
+ "ঐ": 20,
28
+ "ও": 66,
29
+ "ঔ": 59,
30
+ "ক": 33,
31
+ "খ": 51,
32
+ "গ": 41,
33
+ "ঘ": 50,
34
+ "ঙ": 68,
35
+ "চ": 69,
36
+ "ছ": 17,
37
+ "জ": 28,
38
+ "ঝ": 27,
39
+ "ঞ": 22,
40
+ "ট": 11,
41
+ "ঠ": 30,
42
+ "ড": 47,
43
+ "ঢ": 31,
44
+ "ণ": 4,
45
+ "ত": 75,
46
+ "থ": 32,
47
+ "দ": 25,
48
+ "ধ": 29,
49
+ "ন": 15,
50
+ "প": 64,
51
+ "ফ": 37,
52
+ "ব": 40,
53
+ "ভ": 44,
54
+ "ম": 76,
55
+ "য": 8,
56
+ "র": 48,
57
+ "ল": 63,
58
+ "শ": 5,
59
+ "ষ": 7,
60
+ "স": 77,
61
+ "হ": 21,
62
+ "়": 13,
63
+ "া": 2,
64
+ "ি": 70,
65
+ "ী": 3,
66
+ "ু": 71,
67
+ "ূ": 52,
68
+ "ৃ": 60,
69
+ "ে": 62,
70
+ "ৈ": 9,
71
+ "ো": 57,
72
+ "ৌ": 72,
73
+ "্": 38,
74
+ "ৎ": 19,
75
+ "ড়": 42,
76
+ "ঢ়": 61,
77
+ "য়": 36,
78
+ "ৰ": 43,
79
+ "—": 46,
80
+ "’": 10,
81
+ "‚": 45
82
+ }