Hugging Face's logo

MultiBridge
/
wav2vec-LnNor-IPA-ft

Automatic Speech Recognition
Safetensors
English
wav2vec2
phoneme_recognition
IPA
Eval Results
Model card Files
xet
Community
ikrysinska commited on
Commit
3b00792
·
1 Parent(s): fb7978e

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 +30 -0
  4. tokenizer_config.json +105 -0
  5. vocab.json +45 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 44,
3
+ "<s>": 43
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "t͡ʃ",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "14": {
12
+ "content": "oʊ",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "16": {
20
+ "content": "aɪ",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "17": {
28
+ "content": "eɪ",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "22": {
36
+ "content": "ɔɪ",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "38": {
44
+ "content": "d͡ʒ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "39": {
52
+ "content": "aʊ",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "40": {
60
+ "content": "[UNK]",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "41": {
68
+ "content": "[PAD]",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "43": {
76
+ "content": "<s>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "44": {
84
+ "content": "</s>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ }
91
+ },
92
+ "bos_token": "<s>",
93
+ "clean_up_tokenization_spaces": false,
94
+ "do_lower_case": false,
95
+ "eos_token": "</s>",
96
+ "extra_special_tokens": {},
97
+ "model_max_length": 1000000000000000019884624838656,
98
+ "pad_token": "[PAD]",
99
+ "processor_class": "Wav2Vec2Processor",
100
+ "replace_word_delimiter_char": " ",
101
+ "target_lang": null,
102
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
103
+ "unk_token": "[UNK]",
104
+ "word_delimiter_token": " "
105
+ }
vocab.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 42,
3
+ "[PAD]": 41,
4
+ "[UNK]": 40,
5
+ "aɪ": 16,
6
+ "aʊ": 39,
7
+ "b": 21,
8
+ "d": 25,
9
+ "d͡ʒ": 38,
10
+ "eɪ": 17,
11
+ "f": 5,
12
+ "h": 29,
13
+ "i": 13,
14
+ "j": 36,
15
+ "k": 18,
16
+ "l": 4,
17
+ "m": 31,
18
+ "n": 19,
19
+ "oʊ": 14,
20
+ "p": 2,
21
+ "s": 32,
22
+ "t": 35,
23
+ "t͡ʃ": 0,
24
+ "u": 15,
25
+ "v": 6,
26
+ "w": 30,
27
+ "z": 26,
28
+ "æ": 37,
29
+ "ð": 11,
30
+ "ŋ": 8,
31
+ "ɑ": 10,
32
+ "ɔ": 1,
33
+ "ɔɪ": 22,
34
+ "ə": 20,
35
+ "ɛ": 3,
36
+ "ɝ": 23,
37
+ "ɡ": 33,
38
+ "ɪ": 34,
39
+ "ɹ": 7,
40
+ "ʃ": 24,
41
+ "ʊ": 27,
42
+ "ʌ": 12,
43
+ "ʒ": 28,
44
+ "θ": 9
45
+ }