Hugging Face's logo

facebook
/
mms-lid-126

Audio Classification
Transformers
PyTorch
Safetensors
wav2vec2
mms
Inference Endpoints
Model card Files Community
1
patrickvonplaten commited on
Commit
a3ad883
•
1 Parent(s): 939633e

make style

Browse files
Files changed (3) hide show
  1. config.json +236 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./",
3
+ "activation_dropout": 0.05,
4
+ "adapter_attn_dim": 16,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.05,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 1024,
15
+ "codevector_dim": 1024,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.05,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.05,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1280,
59
+ "id2label": {
60
+ "0": "ara",
61
+ "1": "cmn",
62
+ "2": "eng",
63
+ "3": "spa",
64
+ "4": "fra",
65
+ "5": "mlg",
66
+ "6": "swe",
67
+ "7": "por",
68
+ "8": "vie",
69
+ "9": "ful",
70
+ "10": "sun",
71
+ "11": "asm",
72
+ "12": "ben",
73
+ "13": "zlm",
74
+ "14": "kor",
75
+ "15": "ind",
76
+ "16": "hin",
77
+ "17": "tuk",
78
+ "18": "urd",
79
+ "19": "aze",
80
+ "20": "slv",
81
+ "21": "mon",
82
+ "22": "hau",
83
+ "23": "tel",
84
+ "24": "swh",
85
+ "25": "bod",
86
+ "26": "rus",
87
+ "27": "tur",
88
+ "28": "heb",
89
+ "29": "mar",
90
+ "30": "som",
91
+ "31": "tgl",
92
+ "32": "tat",
93
+ "33": "tha",
94
+ "34": "cat",
95
+ "35": "ron",
96
+ "36": "mal",
97
+ "37": "bel",
98
+ "38": "pol",
99
+ "39": "yor",
100
+ "40": "nld",
101
+ "41": "bul",
102
+ "42": "hat",
103
+ "43": "afr",
104
+ "44": "isl",
105
+ "45": "amh",
106
+ "46": "tam",
107
+ "47": "hun",
108
+ "48": "hrv",
109
+ "49": "lit",
110
+ "50": "cym",
111
+ "51": "fas",
112
+ "52": "mkd",
113
+ "53": "ell",
114
+ "54": "bos",
115
+ "55": "deu",
116
+ "56": "sqi",
117
+ "57": "jav",
118
+ "58": "nob",
119
+ "59": "uzb",
120
+ "60": "snd",
121
+ "61": "lat",
122
+ "62": "nya",
123
+ "63": "grn",
124
+ "64": "mya",
125
+ "65": "orm",
126
+ "66": "lin",
127
+ "67": "hye",
128
+ "68": "yue",
129
+ "69": "pan",
130
+ "70": "jpn",
131
+ "71": "kaz",
132
+ "72": "npi",
133
+ "73": "kat",
134
+ "74": "guj",
135
+ "75": "kan",
136
+ "76": "tgk",
137
+ "77": "ukr",
138
+ "78": "ces",
139
+ "79": "lav",
140
+ "80": "bak",
141
+ "81": "khm",
142
+ "82": "fao",
143
+ "83": "glg",
144
+ "84": "ltz",
145
+ "85": "lao",
146
+ "86": "mlt",
147
+ "87": "sin",
148
+ "88": "sna",
149
+ "89": "ita",
150
+ "90": "srp",
151
+ "91": "mri",
152
+ "92": "nno",
153
+ "93": "pus",
154
+ "94": "eus",
155
+ "95": "ory",
156
+ "96": "lug",
157
+ "97": "bre",
158
+ "98": "luo",
159
+ "99": "slk",
160
+ "100": "fin",
161
+ "101": "dan",
162
+ "102": "yid",
163
+ "103": "est",
164
+ "104": "ceb",
165
+ "105": "war",
166
+ "106": "san",
167
+ "107": "kir",
168
+ "108": "oci",
169
+ "109": "wol",
170
+ "110": "haw",
171
+ "111": "kam",
172
+ "112": "umb",
173
+ "113": "xho",
174
+ "114": "epo",
175
+ "115": "zul",
176
+ "116": "ibo",
177
+ "117": "abk",
178
+ "118": "ckb",
179
+ "119": "nso",
180
+ "120": "gle",
181
+ "121": "kea",
182
+ "122": "ast",
183
+ "123": "sco",
184
+ "124": "glv",
185
+ "125": "ina"
186
+ },
187
+ "initializer_range": 0.02,
188
+ "intermediate_size": 5120,
189
+ "layer_norm_eps": 1e-05,
190
+ "layerdrop": 0.05,
191
+ "mask_feature_length": 10,
192
+ "mask_feature_min_masks": 0,
193
+ "mask_feature_prob": 0.0,
194
+ "mask_time_length": 10,
195
+ "mask_time_min_masks": 2,
196
+ "mask_time_prob": 0.05,
197
+ "model_type": "wav2vec2",
198
+ "num_adapter_layers": 3,
199
+ "num_attention_heads": 16,
200
+ "num_codevector_groups": 2,
201
+ "num_codevectors_per_group": 320,
202
+ "num_conv_pos_embedding_groups": 16,
203
+ "num_conv_pos_embeddings": 128,
204
+ "num_feat_extract_layers": 7,
205
+ "num_hidden_layers": 48,
206
+ "num_negatives": 100,
207
+ "output_hidden_size": 1280,
208
+ "pad_token_id": 0,
209
+ "proj_codevector_dim": 1024,
210
+ "tdnn_dilation": [
211
+ 1,
212
+ 2,
213
+ 3,
214
+ 1,
215
+ 1
216
+ ],
217
+ "tdnn_dim": [
218
+ 512,
219
+ 512,
220
+ 512,
221
+ 512,
222
+ 1500
223
+ ],
224
+ "tdnn_kernel": [
225
+ 5,
226
+ 3,
227
+ 3,
228
+ 1,
229
+ 1
230
+ ],
231
+ "torch_dtype": "float32",
232
+ "transformers_version": "4.31.0.dev0",
233
+ "use_weighted_layer_sum": false,
234
+ "vocab_size": 154,
235
+ "xvector_output_dim": 512
236
+ }
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,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4656bddd75fdac0765c21c1cf496ef8eeb6190682d06ad68f7043105d12d9f
3
+ size 3864724503