Hugging Face's logo

sarthak712
/
emotion_detection_model

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sarthak712 commited on
Commit
66f801a
•
1 Parent(s): 513af2b

End of training

Browse files
Files changed (7) hide show
  1. README.md +82 -0
  2. config.json +134 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/Mar18_06-26-24_80e83759156f/events.out.tfevents.1710743263.80e83759156f.34.0 +3 -0
  6. runs/Mar18_06-26-24_80e83759156f/events.out.tfevents.1710758292.80e83759156f.34.1 +3 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: emotion_detection_model
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_detection_model
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6542
21
+ - Accuracy: 0.8291
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-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 128
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 20
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 1.6124 | 0.99 | 70 | 1.5873 | 0.3984 |
56
+ | 1.2504 | 1.99 | 141 | 1.2053 | 0.5963 |
57
+ | 0.833 | 3.0 | 212 | 0.8178 | 0.7504 |
58
+ | 0.6633 | 4.0 | 283 | 0.7137 | 0.7783 |
59
+ | 0.5791 | 4.99 | 353 | 0.6395 | 0.7915 |
60
+ | 0.4472 | 5.99 | 424 | 0.6398 | 0.7968 |
61
+ | 0.378 | 7.0 | 495 | 0.5669 | 0.8145 |
62
+ | 0.2902 | 8.0 | 566 | 0.5777 | 0.8158 |
63
+ | 0.2621 | 8.99 | 636 | 0.6320 | 0.8074 |
64
+ | 0.231 | 9.99 | 707 | 0.6347 | 0.8149 |
65
+ | 0.174 | 11.0 | 778 | 0.6649 | 0.8096 |
66
+ | 0.1781 | 12.0 | 849 | 0.6180 | 0.8211 |
67
+ | 0.1566 | 12.99 | 919 | 0.6311 | 0.8211 |
68
+ | 0.1239 | 13.99 | 990 | 0.6322 | 0.8207 |
69
+ | 0.1223 | 15.0 | 1061 | 0.6443 | 0.8264 |
70
+ | 0.0988 | 16.0 | 1132 | 0.6424 | 0.8255 |
71
+ | 0.0866 | 16.99 | 1202 | 0.6542 | 0.8291 |
72
+ | 0.0661 | 17.99 | 1273 | 0.6748 | 0.8264 |
73
+ | 0.0815 | 19.0 | 1344 | 0.6723 | 0.8286 |
74
+ | 0.0595 | 19.79 | 1400 | 0.6865 | 0.8229 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.37.0
80
+ - Pytorch 2.1.2
81
+ - Datasets 2.1.0
82
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "neutral",
61
+ "1": "disgust",
62
+ "2": "fear",
63
+ "3": "sad",
64
+ "4": "happy",
65
+ "5": "angry"
66
+ },
67
+ "initializer_range": 0.02,
68
+ "intermediate_size": 3072,
69
+ "label2id": {
70
+ "angry": "5",
71
+ "disgust": "1",
72
+ "fear": "2",
73
+ "happy": "4",
74
+ "neutral": "0",
75
+ "sad": "3"
76
+ },
77
+ "layer_norm_eps": 1e-05,
78
+ "layerdrop": 0.0,
79
+ "mask_channel_length": 10,
80
+ "mask_channel_min_space": 1,
81
+ "mask_channel_other": 0.0,
82
+ "mask_channel_prob": 0.0,
83
+ "mask_channel_selection": "static",
84
+ "mask_feature_length": 10,
85
+ "mask_feature_min_masks": 0,
86
+ "mask_feature_prob": 0.0,
87
+ "mask_time_length": 10,
88
+ "mask_time_min_masks": 2,
89
+ "mask_time_min_space": 1,
90
+ "mask_time_other": 0.0,
91
+ "mask_time_prob": 0.05,
92
+ "mask_time_selection": "static",
93
+ "model_type": "wav2vec2",
94
+ "no_mask_channel_overlap": false,
95
+ "no_mask_time_overlap": false,
96
+ "num_adapter_layers": 3,
97
+ "num_attention_heads": 12,
98
+ "num_codevector_groups": 2,
99
+ "num_codevectors_per_group": 320,
100
+ "num_conv_pos_embedding_groups": 16,
101
+ "num_conv_pos_embeddings": 128,
102
+ "num_feat_extract_layers": 7,
103
+ "num_hidden_layers": 12,
104
+ "num_negatives": 100,
105
+ "output_hidden_size": 768,
106
+ "pad_token_id": 0,
107
+ "proj_codevector_dim": 256,
108
+ "tdnn_dilation": [
109
+ 1,
110
+ 2,
111
+ 3,
112
+ 1,
113
+ 1
114
+ ],
115
+ "tdnn_dim": [
116
+ 512,
117
+ 512,
118
+ 512,
119
+ 512,
120
+ 1500
121
+ ],
122
+ "tdnn_kernel": [
123
+ 5,
124
+ 3,
125
+ 3,
126
+ 1,
127
+ 1
128
+ ],
129
+ "torch_dtype": "float32",
130
+ "transformers_version": "4.37.0",
131
+ "use_weighted_layer_sum": false,
132
+ "vocab_size": 32,
133
+ "xvector_output_dim": 512
134
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6081aae41a85a668cd0adc994f7b4678f45b0430de4f405c2e551f44a23e472
3
+ size 378306480
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/Mar18_06-26-24_80e83759156f/events.out.tfevents.1710743263.80e83759156f.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ddf6fccc6528fcac7de4778e3ab1b9064850f8c319e560a9669018afb13a18
3
+ size 35100
runs/Mar18_06-26-24_80e83759156f/events.out.tfevents.1710758292.80e83759156f.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f25480c443f73c3e26cc1a484885567e9e166ebefe81b4f4e33e074ae5b7b08
3
+ size 411
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98633ba79364d2d285800bddf55c34728c8794144c36bfb122fcc8a4364668f1
3
+ size 4728