Hugging Face's logo

sgoedecke
/
wav2vec2_birdcalls

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Model card Files
xet
 Metrics Community
sgoedecke commited on
Commit
7a2245c
·
verified ·
1 Parent(s): 05b4ddb

Training in progress, epoch 0

Browse files
Files changed (5) hide show
  1. config.json +162 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +9 -0
  4. runs/Feb23_22-16-52_209-20-158-204/events.out.tfevents.1708726616.209-20-158-204.2960.1 +3 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
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": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
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": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "sonspa",
61
+ "1": "bncfly",
62
+ "10": "rewbla",
63
+ "11": "rucspa1",
64
+ "12": "gbwwre1",
65
+ "13": "mallar3",
66
+ "14": "swathr",
67
+ "15": "bewwre",
68
+ "16": "barswa",
69
+ "17": "comrav",
70
+ "18": "carwre",
71
+ "19": "rubpep1",
72
+ "2": "houwre",
73
+ "3": "eursta",
74
+ "4": "norcar",
75
+ "5": "houspa",
76
+ "6": "amerob",
77
+ "7": "spotow",
78
+ "8": "redcro",
79
+ "9": "cubthr"
80
+ },
81
+ "initializer_range": 0.02,
82
+ "intermediate_size": 3072,
83
+ "label2id": {
84
+ "amerob": "6",
85
+ "barswa": "16",
86
+ "bewwre": "15",
87
+ "bncfly": "1",
88
+ "carwre": "18",
89
+ "comrav": "17",
90
+ "cubthr": "9",
91
+ "eursta": "3",
92
+ "gbwwre1": "12",
93
+ "houspa": "5",
94
+ "houwre": "2",
95
+ "mallar3": "13",
96
+ "norcar": "4",
97
+ "redcro": "8",
98
+ "rewbla": "10",
99
+ "rubpep1": "19",
100
+ "rucspa1": "11",
101
+ "sonspa": "0",
102
+ "spotow": "7",
103
+ "swathr": "14"
104
+ },
105
+ "layer_norm_eps": 1e-05,
106
+ "layerdrop": 0.0,
107
+ "mask_channel_length": 10,
108
+ "mask_channel_min_space": 1,
109
+ "mask_channel_other": 0.0,
110
+ "mask_channel_prob": 0.0,
111
+ "mask_channel_selection": "static",
112
+ "mask_feature_length": 10,
113
+ "mask_feature_min_masks": 0,
114
+ "mask_feature_prob": 0.0,
115
+ "mask_time_length": 10,
116
+ "mask_time_min_masks": 2,
117
+ "mask_time_min_space": 1,
118
+ "mask_time_other": 0.0,
119
+ "mask_time_prob": 0.05,
120
+ "mask_time_selection": "static",
121
+ "model_type": "wav2vec2",
122
+ "no_mask_channel_overlap": false,
123
+ "no_mask_time_overlap": false,
124
+ "num_adapter_layers": 3,
125
+ "num_attention_heads": 12,
126
+ "num_codevector_groups": 2,
127
+ "num_codevectors_per_group": 320,
128
+ "num_conv_pos_embedding_groups": 16,
129
+ "num_conv_pos_embeddings": 128,
130
+ "num_feat_extract_layers": 7,
131
+ "num_hidden_layers": 12,
132
+ "num_negatives": 100,
133
+ "output_hidden_size": 768,
134
+ "pad_token_id": 0,
135
+ "proj_codevector_dim": 256,
136
+ "tdnn_dilation": [
137
+ 1,
138
+ 2,
139
+ 3,
140
+ 1,
141
+ 1
142
+ ],
143
+ "tdnn_dim": [
144
+ 512,
145
+ 512,
146
+ 512,
147
+ 512,
148
+ 1500
149
+ ],
150
+ "tdnn_kernel": [
151
+ 5,
152
+ 3,
153
+ 3,
154
+ 1,
155
+ 1
156
+ ],
157
+ "torch_dtype": "float32",
158
+ "transformers_version": "4.38.1",
159
+ "use_weighted_layer_sum": false,
160
+ "vocab_size": 32,
161
+ "xvector_output_dim": 512
162
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a2379d142c06ad4c8a6676b1abf3a3ec784bc0e24ed161e789c331bfb6f816
3
+ size 378320824
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
+ }
runs/Feb23_22-16-52_209-20-158-204/events.out.tfevents.1708726616.209-20-158-204.2960.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:127e7f8fb3d772b48f0120e1f441d3be9c468280bdc81330725ea06ea0c3e061
3
+ size 7739
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d35e947e95a7413d43b9827a2d7d89c1bcf1b30d2f94303fecfbc33a35d70e6f
3
+ size 4475