Hugging Face's logo

Piranav
/
wav2vec2-large-mms-1b-mundari-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Piranav commited on
Commit
4643bfb
·
verified ·
1 Parent(s): 06f6159

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