Hugging Face's logo

aoxo
/
wav2vec2-base-mal

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Inference Endpoints
Model card Files Community
aoxo commited on
Commit
8a432f2
•
1 Parent(s): aacef5e

Upload processor

Browse files
Files changed (5) hide show
  1. added_tokens.json +4 -0
  2. preprocessor_config.json +10 -0
  3. special_tokens_map.json +6 -0
  4. tokenizer_config.json +48 -0
  5. vocab.json +87 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 86,
3
+ "<s>": 85
4
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
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
+ "83": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "84": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "85": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "86": {
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": false,
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 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 43,
3
+ "'": 41,
4
+ "[PAD]": 84,
5
+ "[UNK]": 83,
6
+ "_": 77,
7
+ "e": 51,
8
+ "l": 50,
9
+ "r": 74,
10
+ "t": 81,
11
+ "u": 10,
12
+ "ം": 72,
13
+ "ഃ": 38,
14
+ "അ": 14,
15
+ "ആ": 62,
16
+ "ഇ": 44,
17
+ "ഈ": 18,
18
+ "ഉ": 67,
19
+ "ഊ": 12,
20
+ "ഋ": 9,
21
+ "എ": 57,
22
+ "ഏ": 2,
23
+ "ഐ": 26,
24
+ "ഒ": 1,
25
+ "ഓ": 33,
26
+ "ഔ": 75,
27
+ "ക": 82,
28
+ "ഖ": 16,
29
+ "ഗ": 76,
30
+ "ഘ": 80,
31
+ "ങ": 40,
32
+ "ച": 71,
33
+ "ഛ": 70,
34
+ "ജ": 20,
35
+ "ഝ": 60,
36
+ "ഞ": 66,
37
+ "ട": 0,
38
+ "ഠ": 27,
39
+ "ഡ": 47,
40
+ "ഢ": 23,
41
+ "ണ": 53,
42
+ "ത": 58,
43
+ "ഥ": 59,
44
+ "ദ": 39,
45
+ "ധ": 5,
46
+ "ന": 65,
47
+ "പ": 4,
48
+ "ഫ": 42,
49
+ "ബ": 55,
50
+ "ഭ": 73,
51
+ "മ": 21,
52
+ "യ": 78,
53
+ "ര": 11,
54
+ "റ": 7,
55
+ "ല": 45,
56
+ "ള": 24,
57
+ "ഴ": 8,
58
+ "വ": 68,
59
+ "ശ": 63,
60
+ "ഷ": 54,
61
+ "സ": 22,
62
+ "ഹ": 37,
63
+ "ാ": 64,
64
+ "ി": 49,
65
+ "ീ": 30,
66
+ "ു": 35,
67
+ "ൂ": 17,
68
+ "ൃ": 28,
69
+ "െ": 69,
70
+ "േ": 13,
71
+ "ൈ": 15,
72
+ "ൊ": 56,
73
+ "ോ": 79,
74
+ "ൌ": 19,
75
+ "്": 36,
76
+ "ൗ": 3,
77
+ "ൺ": 29,
78
+ "ൻ": 32,
79
+ "ർ": 48,
80
+ "ൽ": 34,
81
+ "ൾ": 25,
82
+ "‌": 46,
83
+ "‍": 6,
84
+ "‎": 61,
85
+ "“": 52,
86
+ "”": 31
87
+ }