Hugging Face's logo

Abhilashvj
/
w2v-bert-2.0-malayalam-colab-CV16.0

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Abhilashvj commited on
Commit
6a54174
•
1 Parent(s): 0fdb8bc

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 +74 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 73,
3
+ "<s>": 72
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
+ "70": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "71": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "72": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "73": {
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": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 71,
3
+ "[UNK]": 70,
4
+ "|": 0,
5
+ "ം": 1,
6
+ "ഃ": 2,
7
+ "അ": 3,
8
+ "ആ": 4,
9
+ "ഇ": 5,
10
+ "ഈ": 6,
11
+ "ഉ": 7,
12
+ "ഊ": 8,
13
+ "എ": 9,
14
+ "ഏ": 10,
15
+ "ഐ": 11,
16
+ "ഒ": 12,
17
+ "ഓ": 13,
18
+ "ക": 14,
19
+ "ഖ": 15,
20
+ "ഗ": 16,
21
+ "ഘ": 17,
22
+ "ങ": 18,
23
+ "ച": 19,
24
+ "ഛ": 20,
25
+ "ജ": 21,
26
+ "ഞ": 22,
27
+ "ട": 23,
28
+ "ഠ": 24,
29
+ "ഡ": 25,
30
+ "ഢ": 26,
31
+ "ണ": 27,
32
+ "ത": 28,
33
+ "ഥ": 29,
34
+ "ദ": 30,
35
+ "ധ": 31,
36
+ "ന": 32,
37
+ "പ": 33,
38
+ "ഫ": 34,
39
+ "ബ": 35,
40
+ "ഭ": 36,
41
+ "മ": 37,
42
+ "യ": 38,
43
+ "ര": 39,
44
+ "റ": 40,
45
+ "ല": 41,
46
+ "ള": 42,
47
+ "ഴ": 43,
48
+ "വ": 44,
49
+ "ശ": 45,
50
+ "ഷ": 46,
51
+ "സ": 47,
52
+ "ഹ": 48,
53
+ "ാ": 49,
54
+ "ി": 50,
55
+ "ീ": 51,
56
+ "ു": 52,
57
+ "ൂ": 53,
58
+ "ൃ": 54,
59
+ "െ": 55,
60
+ "േ": 56,
61
+ "ൈ": 57,
62
+ "ൊ": 58,
63
+ "ോ": 59,
64
+ "ൌ": 60,
65
+ "്": 61,
66
+ "ൗ": 62,
67
+ "ൺ": 63,
68
+ "ൻ": 64,
69
+ "ർ": 65,
70
+ "ൽ": 66,
71
+ "ൾ": 67,
72
+ "ൿ": 68,
73
+ "’": 69
74
+ }