Hugging Face's logo

carlynamazed24
/
wav2vec2-chabacano-stt-v2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
carlynamazed24 commited on
Commit
dc2fc90
·
verified ·
1 Parent(s): d53fe9f

End of training

Browse files
Files changed (4) hide show
  1. best_model/added_tokens.json +4 -0
  2. best_model/special_tokens_map.json +30 -0
  3. best_model/tokenizer_config.json +49 -0
  4. best_model/vocab.json +89 -0
best_model/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 88,
3
+ "<s>": 87
4
+ }
best_model/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
best_model/tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "85": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "86": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "87": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "88": {
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
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "target_lang": null,
46
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
47
+ "unk_token": "[UNK]",
48
+ "word_delimiter_token": "|"
49
+ }
best_model/vocab.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 1,
3
+ "$": 2,
4
+ "'": 3,
5
+ ",": 4,
6
+ "-": 5,
7
+ ".": 6,
8
+ "0": 7,
9
+ "1": 8,
10
+ "2": 9,
11
+ "3": 10,
12
+ "4": 11,
13
+ "5": 12,
14
+ "6": 13,
15
+ "7": 14,
16
+ "8": 15,
17
+ "9": 16,
18
+ "?": 17,
19
+ "A": 18,
20
+ "B": 19,
21
+ "C": 20,
22
+ "D": 21,
23
+ "E": 22,
24
+ "F": 23,
25
+ "G": 24,
26
+ "H": 25,
27
+ "I": 26,
28
+ "J": 27,
29
+ "K": 28,
30
+ "L": 29,
31
+ "M": 30,
32
+ "N": 31,
33
+ "O": 32,
34
+ "P": 33,
35
+ "Q": 34,
36
+ "R": 35,
37
+ "S": 36,
38
+ "T": 37,
39
+ "U": 38,
40
+ "V": 39,
41
+ "W": 40,
42
+ "Y": 41,
43
+ "Z": 42,
44
+ "[PAD]": 86,
45
+ "[UNK]": 85,
46
+ "a": 43,
47
+ "b": 44,
48
+ "c": 45,
49
+ "d": 46,
50
+ "e": 47,
51
+ "f": 48,
52
+ "g": 49,
53
+ "h": 50,
54
+ "i": 51,
55
+ "j": 52,
56
+ "k": 53,
57
+ "l": 54,
58
+ "m": 55,
59
+ "n": 56,
60
+ "o": 57,
61
+ "p": 58,
62
+ "q": 59,
63
+ "r": 60,
64
+ "s": 61,
65
+ "t": 62,
66
+ "u": 63,
67
+ "v": 64,
68
+ "w": 65,
69
+ "x": 66,
70
+ "y": 67,
71
+ "z": 68,
72
+ "|": 0,
73
+ "¡": 69,
74
+ "¿": 70,
75
+ "Á": 71,
76
+ "É": 72,
77
+ "Í": 73,
78
+ "Ñ": 74,
79
+ "Ó": 75,
80
+ "Ú": 76,
81
+ "á": 77,
82
+ "é": 78,
83
+ "í": 79,
84
+ "ñ": 80,
85
+ "ó": 81,
86
+ "ú": 82,
87
+ "ü": 83,
88
+ "今": 84
89
+ }