Hugging Face's logo

davidbae
/
ipa-asr

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Model card Files
xet
Community
davidbae commited on
Commit
e019c0e
·
verified ·
1 Parent(s): fe431d4

v2

Browse files
Files changed (7) hide show
  1. added_tokens.json +4 -0
  2. config.json +1 -1
  3. model.safetensors +2 -2
  4. preprocessor_config.json +9 -0
  5. special_tokens_map.json +6 -0
  6. tokenizer_config.json +209 -0
  7. vocab.json +41 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 40,
3
+ "<s>": 39
4
+ }
config.json CHANGED
@@ -7,7 +7,7 @@
7
  "add_adapter": false,
8
  "apply_spec_augment": true,
9
  "architectures": [
10
- "Wav2Vec2Model"
11
  ],
12
  "attention_dropout": 0.1,
13
  "bos_token_id": 1,
 
7
  "add_adapter": false,
8
  "apply_spec_augment": true,
9
  "architectures": [
10
+ "Wav2Vec2ForCTC"
11
  ],
12
  "attention_dropout": 0.1,
13
  "bos_token_id": 1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea363dcaf7fffa3f4df8405cdfcfebec01c81d380736b5e36b912e45616bb1e5
3
- size 377510632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27be2981996a73d88f5dc9c345fea36eb4d5cc1aa2b5c95439919d35267928b7
3
+ size 377638812
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
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 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "2": {
4
+ "content": "tʰ",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "3": {
12
+ "content": "tɕ",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "4": {
20
+ "content": "tɕ*",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "5": {
28
+ "content": "tɕʰ",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "8": {
36
+ "content": "k*",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "9": {
44
+ "content": "kʰ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "14": {
52
+ "content": "t*",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "15": {
60
+ "content": "p*",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "16": {
68
+ "content": "pʰ",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "18": {
76
+ "content": "s*",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "23": {
84
+ "content": "wɛ",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "27": {
92
+ "content": "ɰi",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "28": {
100
+ "content": "jo",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "29": {
108
+ "content": "ju",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "30": {
116
+ "content": "ja",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "31": {
124
+ "content": "jʌ",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "32": {
132
+ "content": "jɛ",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "33": {
140
+ "content": "wa",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "34": {
148
+ "content": "wʌ",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "35": {
156
+ "content": "wi",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "37": {
164
+ "content": "[UNK]",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "38": {
172
+ "content": "[PAD]",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "39": {
180
+ "content": "<s>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "40": {
188
+ "content": "</s>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ }
195
+ },
196
+ "bos_token": "<s>",
197
+ "clean_up_tokenization_spaces": true,
198
+ "do_lower_case": false,
199
+ "do_normalize": true,
200
+ "eos_token": "</s>",
201
+ "model_max_length": 1000000000000000019884624838656,
202
+ "pad_token": "[PAD]",
203
+ "replace_word_delimiter_char": " ",
204
+ "return_attention_mask": false,
205
+ "target_lang": null,
206
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
207
+ "unk_token": "[UNK]",
208
+ "word_delimiter_token": "|"
209
+ }
vocab.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 38,
3
+ "[UNK]": 37,
4
+ "h": 7,
5
+ "i": 21,
6
+ "ja": 30,
7
+ "jo": 28,
8
+ "ju": 29,
9
+ "jɛ": 32,
10
+ "jʌ": 31,
11
+ "k": 6,
12
+ "k*": 8,
13
+ "kʰ": 9,
14
+ "l": 10,
15
+ "m": 11,
16
+ "n": 12,
17
+ "o": 22,
18
+ "p": 0,
19
+ "p*": 15,
20
+ "pʰ": 16,
21
+ "s": 17,
22
+ "s*": 18,
23
+ "t": 1,
24
+ "t*": 14,
25
+ "tɕ": 3,
26
+ "tɕ*": 4,
27
+ "tɕʰ": 5,
28
+ "tʰ": 2,
29
+ "u": 24,
30
+ "wa": 33,
31
+ "wi": 35,
32
+ "wɛ": 23,
33
+ "wʌ": 34,
34
+ "|": 36,
35
+ "ŋ": 13,
36
+ "ɑ": 19,
37
+ "ɛ": 20,
38
+ "ɯ": 26,
39
+ "ɰi": 27,
40
+ "ʌ": 25
41
+ }