Lachin commited on
Commit
2ed0e50
·
verified ·
1 Parent(s): 83221cf

Lachin/birds_sound_model

Browse files
Files changed (5) hide show
  1. README.md +65 -0
  2. config.json +214 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: dima806/bird_sounds_classification
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: emotion_recognition
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # emotion_recognition
17
+
18
+ This model is a fine-tuned version of [dima806/bird_sounds_classification](https://huggingface.co/dima806/bird_sounds_classification) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7880
21
+ - Accuracy: 0.8249
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 3e-06
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 50
47
+ - num_epochs: 5
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
+ | 0.7843 | 1.0 | 4899 | 0.9654 | 0.7514 |
54
+ | 0.6352 | 2.0 | 9798 | 0.9026 | 0.7955 |
55
+ | 0.0438 | 3.0 | 14697 | 0.8320 | 0.8037 |
56
+ | 0.443 | 4.0 | 19596 | 0.8014 | 0.8131 |
57
+ | 0.3585 | 5.0 | 24495 | 0.7880 | 0.8249 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.41.2
63
+ - Pytorch 2.3.0+cu121
64
+ - Datasets 2.19.2
65
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dima806/bird_sounds_classification",
3
+ "activation_dropout": 0.1,
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_dropout": 0.0,
52
+ "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "id2label": {
62
+ "0": "Andean Guan",
63
+ "1": "Andean Tinamou",
64
+ "2": "Australian Brushturkey",
65
+ "3": "Band-tailed Guan",
66
+ "4": "Bartletts Tinamou",
67
+ "5": "Bearded Guan",
68
+ "6": "Black-capped Tinamou",
69
+ "7": "Blue-throated Piping Guan",
70
+ "8": "Brazilian Tinamou",
71
+ "9": "Brown Tinamou",
72
+ "10": "Brushland Tinamou",
73
+ "11": "Cauca Guan",
74
+ "12": "Chaco Chachalaca",
75
+ "13": "Chestnut-winged Chachalaca",
76
+ "14": "Cinereous Tinamou",
77
+ "15": "Colombian Chachalaca",
78
+ "16": "Crested Guan",
79
+ "17": "Dusky Megapode",
80
+ "18": "Dusky-legged Guan",
81
+ "19": "Dwarf Tinamou",
82
+ "20": "Great Tinamou",
83
+ "21": "Grey Tinamou",
84
+ "22": "Grey-headed Chachalaca",
85
+ "23": "Highland Tinamou",
86
+ "24": "Little Chachalaca",
87
+ "25": "Little Tinamou",
88
+ "26": "Orange-footed Scrubfowl",
89
+ "27": "Pale-browed Tinamou",
90
+ "28": "Plain Chachalaca",
91
+ "29": "Red-legged Tinamou",
92
+ "30": "Red-winged Tinamou",
93
+ "31": "Rufous-bellied Chachalaca",
94
+ "32": "Rufous-headed Chachalaca",
95
+ "33": "Rufous-vented Chachalaca",
96
+ "34": "Rusty-margined Guan",
97
+ "35": "Slaty-breasted Tinamou",
98
+ "36": "Small-billed Tinamou",
99
+ "37": "Solitary Tinamou",
100
+ "38": "Speckled Chachalaca",
101
+ "39": "Spixs Guan",
102
+ "40": "Spotted Nothura",
103
+ "41": "Tataupa Tinamou",
104
+ "42": "Tawny-breasted Tinamou",
105
+ "43": "Thicket Tinamou",
106
+ "44": "Undulated Tinamou",
107
+ "45": "Variegated Tinamou",
108
+ "46": "West Mexican Chachalaca",
109
+ "47": "White-bellied Nothura",
110
+ "48": "White-throated Tinamou",
111
+ "49": "Yellow-legged Tinamou"
112
+ },
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 3072,
115
+ "label2id": {
116
+ "LABEL_0": 0,
117
+ "LABEL_1": 1,
118
+ "LABEL_10": 10,
119
+ "LABEL_11": 11,
120
+ "LABEL_12": 12,
121
+ "LABEL_13": 13,
122
+ "LABEL_14": 14,
123
+ "LABEL_15": 15,
124
+ "LABEL_16": 16,
125
+ "LABEL_17": 17,
126
+ "LABEL_18": 18,
127
+ "LABEL_19": 19,
128
+ "LABEL_2": 2,
129
+ "LABEL_20": 20,
130
+ "LABEL_21": 21,
131
+ "LABEL_22": 22,
132
+ "LABEL_23": 23,
133
+ "LABEL_24": 24,
134
+ "LABEL_25": 25,
135
+ "LABEL_26": 26,
136
+ "LABEL_27": 27,
137
+ "LABEL_28": 28,
138
+ "LABEL_29": 29,
139
+ "LABEL_3": 3,
140
+ "LABEL_30": 30,
141
+ "LABEL_31": 31,
142
+ "LABEL_32": 32,
143
+ "LABEL_33": 33,
144
+ "LABEL_34": 34,
145
+ "LABEL_35": 35,
146
+ "LABEL_36": 36,
147
+ "LABEL_37": 37,
148
+ "LABEL_38": 38,
149
+ "LABEL_39": 39,
150
+ "LABEL_4": 4,
151
+ "LABEL_40": 40,
152
+ "LABEL_41": 41,
153
+ "LABEL_42": 42,
154
+ "LABEL_43": 43,
155
+ "LABEL_44": 44,
156
+ "LABEL_45": 45,
157
+ "LABEL_46": 46,
158
+ "LABEL_47": 47,
159
+ "LABEL_48": 48,
160
+ "LABEL_49": 49,
161
+ "LABEL_5": 5,
162
+ "LABEL_6": 6,
163
+ "LABEL_7": 7,
164
+ "LABEL_8": 8,
165
+ "LABEL_9": 9
166
+ },
167
+ "layer_norm_eps": 1e-05,
168
+ "layerdrop": 0.1,
169
+ "mask_feature_length": 10,
170
+ "mask_feature_min_masks": 0,
171
+ "mask_feature_prob": 0.0,
172
+ "mask_time_length": 10,
173
+ "mask_time_min_masks": 2,
174
+ "mask_time_prob": 0.05,
175
+ "model_type": "wav2vec2",
176
+ "num_adapter_layers": 3,
177
+ "num_attention_heads": 12,
178
+ "num_codevector_groups": 2,
179
+ "num_codevectors_per_group": 320,
180
+ "num_conv_pos_embedding_groups": 16,
181
+ "num_conv_pos_embeddings": 128,
182
+ "num_feat_extract_layers": 7,
183
+ "num_hidden_layers": 12,
184
+ "num_negatives": 100,
185
+ "output_hidden_size": 768,
186
+ "pad_token_id": 0,
187
+ "proj_codevector_dim": 256,
188
+ "tdnn_dilation": [
189
+ 1,
190
+ 2,
191
+ 3,
192
+ 1,
193
+ 1
194
+ ],
195
+ "tdnn_dim": [
196
+ 512,
197
+ 512,
198
+ 512,
199
+ 512,
200
+ 1500
201
+ ],
202
+ "tdnn_kernel": [
203
+ 5,
204
+ 3,
205
+ 3,
206
+ 1,
207
+ 1
208
+ ],
209
+ "torch_dtype": "float32",
210
+ "transformers_version": "4.41.2",
211
+ "use_weighted_layer_sum": false,
212
+ "vocab_size": 32,
213
+ "xvector_output_dim": 512
214
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61fb55b951e28111b2e03f563bb98c9447c85fb2a7dd780943f9d188d64fed5
3
+ size 378351720
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3287fc02df059666254b99f7022cb332fc1d23ba9a0e98c21a7b78bde52b27a8
3
+ size 5048