Wiggels commited on
Commit
4699e81
1 Parent(s): ce7240c

End of training

Browse files
Files changed (5) hide show
  1. README.md +54 -0
  2. config.json +136 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - en
5
+ license: apache-2.0
6
+ base_model: facebook/wav2vec2-base
7
+ tags:
8
+ - generated_from_trainer
9
+ datasets:
10
+ - emotion
11
+ model-index:
12
+ - name: Wav2Vec2 Emotion Recognition
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # Wav2Vec2 Emotion Recognition
20
+
21
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the Emotion dataset dataset.
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: 1e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
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: 500
47
+ - training_steps: 4000
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.45.1
52
+ - Pytorch 2.4.1+cu121
53
+ - Datasets 3.0.1
54
+ - Tokenizers 0.20.0
config.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "superb/wav2vec2-base-superb-er",
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": "LABEL_0",
61
+ "1": "LABEL_1",
62
+ "2": "LABEL_2",
63
+ "3": "LABEL_3",
64
+ "4": "LABEL_4",
65
+ "5": "LABEL_5",
66
+ "6": "LABEL_6"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 3072,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_2": 2,
74
+ "LABEL_3": 3,
75
+ "LABEL_4": 4,
76
+ "LABEL_5": 5,
77
+ "LABEL_6": 6
78
+ },
79
+ "layer_norm_eps": 1e-05,
80
+ "layerdrop": 0.05,
81
+ "mask_channel_length": 10,
82
+ "mask_channel_min_space": 1,
83
+ "mask_channel_other": 0.0,
84
+ "mask_channel_prob": 0.0,
85
+ "mask_channel_selection": "static",
86
+ "mask_feature_length": 10,
87
+ "mask_feature_min_masks": 0,
88
+ "mask_feature_prob": 0.0,
89
+ "mask_time_length": 10,
90
+ "mask_time_min_masks": 2,
91
+ "mask_time_min_space": 1,
92
+ "mask_time_other": 0.0,
93
+ "mask_time_prob": 0.05,
94
+ "mask_time_selection": "static",
95
+ "model_type": "wav2vec2",
96
+ "no_mask_channel_overlap": false,
97
+ "no_mask_time_overlap": false,
98
+ "num_adapter_layers": 3,
99
+ "num_attention_heads": 12,
100
+ "num_codevector_groups": 2,
101
+ "num_codevectors_per_group": 320,
102
+ "num_conv_pos_embedding_groups": 16,
103
+ "num_conv_pos_embeddings": 128,
104
+ "num_feat_extract_layers": 7,
105
+ "num_hidden_layers": 12,
106
+ "num_negatives": 100,
107
+ "output_hidden_size": 768,
108
+ "pad_token_id": 0,
109
+ "proj_codevector_dim": 256,
110
+ "tdnn_dilation": [
111
+ 1,
112
+ 2,
113
+ 3,
114
+ 1,
115
+ 1
116
+ ],
117
+ "tdnn_dim": [
118
+ 512,
119
+ 512,
120
+ 512,
121
+ 512,
122
+ 1500
123
+ ],
124
+ "tdnn_kernel": [
125
+ 5,
126
+ 3,
127
+ 3,
128
+ 1,
129
+ 1
130
+ ],
131
+ "torch_dtype": "float32",
132
+ "transformers_version": "4.45.1",
133
+ "use_weighted_layer_sum": true,
134
+ "vocab_size": 32,
135
+ "xvector_output_dim": 512
136
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eeaa53a34a6c672c7fdbbf34c4161d9d642b5249237d2d7ecf385c0839577af
3
+ size 378307632
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 sha256:1e1260b7facf3a8c53eb4d259fe5874904b9f409245fa412b2e560af41912ba4
3
+ size 5240