Hugging Face's logo

Or4kool
/
wolof_asr

Automatic Speech Recognition
Transformers
Safetensors
Wolof
wav2vec2
audio
wolof
ctc
Model card Files
xet
 Community
Or4kool commited on
Commit
ead342e
·
verified ·
1 Parent(s): a59db95

Upload processor

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. processor_config.json +12 -0
  3. tokenizer_config.json +56 -0
  4. vocab.json +77 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 76,
3
+ "<s>": 75
4
+ }
processor_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "do_normalize": true,
4
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
5
+ "feature_size": 1,
6
+ "padding_side": "right",
7
+ "padding_value": 0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ },
11
+ "processor_class": "Wav2Vec2Processor"
12
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "42": {
4
+ "content": "|",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "73": {
12
+ "content": "[UNK]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "74": {
20
+ "content": "[PAD]",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "75": {
28
+ "content": "<s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "76": {
36
+ "content": "</s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "backend": "custom",
45
+ "bos_token": "<s>",
46
+ "do_lower_case": false,
47
+ "eos_token": "</s>",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "processor_class": "Wav2Vec2Processor",
51
+ "replace_word_delimiter_char": " ",
52
+ "target_lang": null,
53
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
54
+ "unk_token": "[UNK]",
55
+ "word_delimiter_token": "|"
56
+ }
vocab.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "$": 0,
3
+ "&": 1,
4
+ "+": 2,
5
+ "/": 3,
6
+ "0": 4,
7
+ "1": 5,
8
+ "2": 6,
9
+ "3": 7,
10
+ "4": 8,
11
+ "5": 9,
12
+ "6": 10,
13
+ "7": 11,
14
+ "8": 12,
15
+ "9": 13,
16
+ "<": 14,
17
+ ">": 15,
18
+ "[PAD]": 74,
19
+ "[UNK]": 73,
20
+ "a": 16,
21
+ "b": 17,
22
+ "c": 18,
23
+ "d": 19,
24
+ "e": 20,
25
+ "f": 21,
26
+ "g": 22,
27
+ "h": 23,
28
+ "i": 24,
29
+ "j": 25,
30
+ "k": 26,
31
+ "l": 27,
32
+ "m": 28,
33
+ "n": 29,
34
+ "o": 30,
35
+ "p": 31,
36
+ "q": 32,
37
+ "r": 33,
38
+ "s": 34,
39
+ "t": 35,
40
+ "u": 36,
41
+ "v": 37,
42
+ "w": 38,
43
+ "x": 39,
44
+ "y": 40,
45
+ "z": 41,
46
+ "|": 42,
47
+ "«": 43,
48
+ "°": 44,
49
+ "µ": 45,
50
+ "»": 46,
51
+ "à": 47,
52
+ "á": 48,
53
+ "â": 49,
54
+ "ã": 50,
55
+ "ç": 51,
56
+ "è": 52,
57
+ "é": 53,
58
+ "ê": 54,
59
+ "ë": 55,
60
+ "í": 56,
61
+ "î": 57,
62
+ "ï": 58,
63
+ "ñ": 59,
64
+ "ó": 60,
65
+ "ô": 61,
66
+ "õ": 62,
67
+ "ö": 63,
68
+ "ù": 64,
69
+ "û": 65,
70
+ "ü": 66,
71
+ "ŋ": 67,
72
+ "œ": 68,
73
+ "—": 69,
74
+ "‘": 70,
75
+ "’": 71,
76
+ "”": 72
77
+ }