Hugging Face's logo

Supreeta03
/
wav2vec2-base-sentiment-analysis-CREMA

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
Supreeta03 commited on
Commit
268fcdb
·
verified ·
1 Parent(s): 8f2c72e

Supreeta03/wav2vec2-base-sentimentAnalysis-CREMA

Browse files
Files changed (7) hide show
  1. README.md +83 -0
  2. config.json +134 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/Apr11_12-04-38_734dde6e3296/events.out.tfevents.1712837085.734dde6e3296.193.6 +3 -0
  6. runs/Apr11_12-04-38_734dde6e3296/events.out.tfevents.1712840184.734dde6e3296.193.7 +3 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: wav2vec-best-CREMA-sentiment-analysis-best3
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
+ # wav2vec-best-CREMA-sentiment-analysis-best3
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Top2 Accuracy: 0.7824
21
+ - Loss: 1.1563
22
+ - Accuracy: 0.5601
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 128
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 20
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Top2 Accuracy | Validation Loss | Accuracy |
55
+ |:-------------:|:-----:|:----:|:-------------:|:---------------:|:--------:|
56
+ | 1.7555 | 0.99 | 37 | 0.5281 | 1.7048 | 0.2905 |
57
+ | 1.5612 | 1.99 | 74 | 0.5819 | 1.5406 | 0.3493 |
58
+ | 1.4333 | 2.98 | 111 | 0.6373 | 1.4668 | 0.3778 |
59
+ | 1.3933 | 4.0 | 149 | 0.6809 | 1.3798 | 0.4450 |
60
+ | 1.3418 | 4.99 | 186 | 0.7045 | 1.3120 | 0.4719 |
61
+ | 1.2238 | 5.99 | 223 | 0.7263 | 1.2718 | 0.4979 |
62
+ | 1.1896 | 6.98 | 260 | 0.7313 | 1.2430 | 0.5113 |
63
+ | 1.1501 | 8.0 | 298 | 0.7296 | 1.2631 | 0.5088 |
64
+ | 1.1052 | 8.99 | 335 | 0.7506 | 1.2462 | 0.5097 |
65
+ | 1.068 | 9.99 | 372 | 0.7641 | 1.1822 | 0.5399 |
66
+ | 1.0594 | 10.98 | 409 | 0.7590 | 1.1700 | 0.5575 |
67
+ | 0.9519 | 12.0 | 447 | 0.7733 | 1.1465 | 0.5516 |
68
+ | 0.9513 | 12.99 | 484 | 0.7918 | 1.1428 | 0.5676 |
69
+ | 0.9324 | 13.99 | 521 | 0.7666 | 1.1721 | 0.5634 |
70
+ | 0.9173 | 14.98 | 558 | 0.7825 | 1.1494 | 0.5584 |
71
+ | 0.8781 | 16.0 | 596 | 0.7918 | 1.1468 | 0.5718 |
72
+ | 0.8627 | 16.99 | 633 | 0.7775 | 1.1554 | 0.5575 |
73
+ | 0.83 | 17.99 | 670 | 0.7817 | 1.1438 | 0.5718 |
74
+ | 0.8305 | 18.98 | 707 | 0.7935 | 1.1323 | 0.5760 |
75
+ | 0.8314 | 19.87 | 740 | 0.7851 | 1.1341 | 0.5726 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.38.2
81
+ - Pytorch 2.2.1+cu121
82
+ - Datasets 2.18.0
83
+ - Tokenizers 0.15.2
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": "Anger",
61
+ "1": "Happy",
62
+ "2": "Fear",
63
+ "3": "Sad",
64
+ "4": "Disgust",
65
+ "5": "Neutral"
66
+ },
67
+ "initializer_range": 0.02,
68
+ "intermediate_size": 3072,
69
+ "label2id": {
70
+ "Anger": 0,
71
+ "Disgust": 4,
72
+ "Fear": 2,
73
+ "Happy": 1,
74
+ "Neutral": 5,
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": "4.38.2",
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 sha256:5548cb17787c54702f06c19fd2a08f8b75ae87f3455e9f77fd6f2c4e8f6066d2
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/Apr11_12-04-38_734dde6e3296/events.out.tfevents.1712837085.734dde6e3296.193.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a533a180209e785e7c5fb593799290c23e5503e21922cc96cdf1e6d7f63101
3
+ size 30100
runs/Apr11_12-04-38_734dde6e3296/events.out.tfevents.1712840184.734dde6e3296.193.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1d3b65caa7e3fcc9c018a54ea81360072b4b64147aa4e983616f5a3a6875f9
3
+ size 468
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba89eead0e34d40b3e04e5c43264409a84a152971c22689e44917c265aa6d0b5
3
+ size 4984