Hugging Face's logo

ameerazam08
/
wav2vec2-xlsr-ravdess-speech-emotion-recognition-final

Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Inference Endpoints
Model card Files Metrics Community
1
ameerazam08 commited on
Commit
5e5ecb6
·
1 Parent(s): 9e57aee

Done

Browse files
Files changed (4) hide show
  1. .ipynb_checkpoints/config-checkpoint.json +131 -0
  2. .ipynb_checkpoints/preprocessor_config-checkpoint.json +10 -0
  3. .ipynb_checkpoints/trainer_state-checkpoint.json +121 -0
  4. preprocessor_config.json +3 -3
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
3
+ "activation_dropout": 0.05,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSpeechClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": true,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.05,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "finetuning_task": "wav2vec2_clf",
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1024,
59
+ "id2label": {
60
+ "0": "angry",
61
+ "1": "fearful",
62
+ "2": "happy",
63
+ "3": "neutral"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 4096,
67
+ "label2id": {
68
+ "angry": 0,
69
+ "fearful": 1,
70
+ "happy": 2,
71
+ "neutral": 3
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "layerdrop": 0.05,
75
+ "mask_channel_length": 10,
76
+ "mask_channel_min_space": 1,
77
+ "mask_channel_other": 0.0,
78
+ "mask_channel_prob": 0.0,
79
+ "mask_channel_selection": "static",
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_min_space": 1,
86
+ "mask_time_other": 0.0,
87
+ "mask_time_prob": 0.05,
88
+ "mask_time_selection": "static",
89
+ "model_type": "wav2vec2",
90
+ "num_adapter_layers": 3,
91
+ "num_attention_heads": 16,
92
+ "num_codevector_groups": 2,
93
+ "num_codevectors_per_group": 320,
94
+ "num_conv_pos_embedding_groups": 16,
95
+ "num_conv_pos_embeddings": 128,
96
+ "num_feat_extract_layers": 7,
97
+ "num_hidden_layers": 24,
98
+ "num_negatives": 100,
99
+ "output_hidden_size": 1024,
100
+ "pad_token_id": 0,
101
+ "pooling_mode": "mean",
102
+ "problem_type": "single_label_classification",
103
+ "proj_codevector_dim": 256,
104
+ "push_to_hub": true,
105
+ "tdnn_dilation": [
106
+ 1,
107
+ 2,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "tdnn_dim": [
113
+ 512,
114
+ 512,
115
+ 512,
116
+ 512,
117
+ 1500
118
+ ],
119
+ "tdnn_kernel": [
120
+ 5,
121
+ 3,
122
+ 3,
123
+ 1,
124
+ 1
125
+ ],
126
+ "torch_dtype": "float32",
127
+ "transformers_version": "4.23.0.dev0",
128
+ "use_weighted_layer_sum": false,
129
+ "vocab_size": 33,
130
+ "xvector_output_dim": 512
131
+ }
.ipynb_checkpoints/preprocessor_config-checkpoint.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
.ipynb_checkpoints/trainer_state-checkpoint.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9166666666666665,
5
+ "global_step": 70,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.42,
12
+ "learning_rate": 8.611111111111112e-05,
13
+ "loss": 1.4322,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.42,
18
+ "eval_accuracy": 0.3125,
19
+ "eval_loss": 1.3030599355697632,
20
+ "eval_runtime": 9.8316,
21
+ "eval_samples_per_second": 4.882,
22
+ "eval_steps_per_second": 1.221,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.83,
27
+ "learning_rate": 7.222222222222222e-05,
28
+ "loss": 1.2975,
29
+ "step": 20
30
+ },
31
+ {
32
+ "epoch": 0.83,
33
+ "eval_accuracy": 0.3541666567325592,
34
+ "eval_loss": 1.2456461191177368,
35
+ "eval_runtime": 12.762,
36
+ "eval_samples_per_second": 3.761,
37
+ "eval_steps_per_second": 0.94,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 1.25,
42
+ "learning_rate": 5.833333333333334e-05,
43
+ "loss": 1.3053,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 1.25,
48
+ "eval_accuracy": 0.375,
49
+ "eval_loss": 1.235076904296875,
50
+ "eval_runtime": 9.8907,
51
+ "eval_samples_per_second": 4.853,
52
+ "eval_steps_per_second": 1.213,
53
+ "step": 30
54
+ },
55
+ {
56
+ "epoch": 1.67,
57
+ "learning_rate": 4.4444444444444447e-05,
58
+ "loss": 1.2042,
59
+ "step": 40
60
+ },
61
+ {
62
+ "epoch": 1.67,
63
+ "eval_accuracy": 0.375,
64
+ "eval_loss": 1.1900380849838257,
65
+ "eval_runtime": 12.1455,
66
+ "eval_samples_per_second": 3.952,
67
+ "eval_steps_per_second": 0.988,
68
+ "step": 40
69
+ },
70
+ {
71
+ "epoch": 2.08,
72
+ "learning_rate": 3.055555555555556e-05,
73
+ "loss": 1.0192,
74
+ "step": 50
75
+ },
76
+ {
77
+ "epoch": 2.08,
78
+ "eval_accuracy": 0.5416666865348816,
79
+ "eval_loss": 1.006090760231018,
80
+ "eval_runtime": 9.9246,
81
+ "eval_samples_per_second": 4.836,
82
+ "eval_steps_per_second": 1.209,
83
+ "step": 50
84
+ },
85
+ {
86
+ "epoch": 2.5,
87
+ "learning_rate": 1.6666666666666667e-05,
88
+ "loss": 0.8874,
89
+ "step": 60
90
+ },
91
+ {
92
+ "epoch": 2.5,
93
+ "eval_accuracy": 0.625,
94
+ "eval_loss": 0.8699900507926941,
95
+ "eval_runtime": 11.1183,
96
+ "eval_samples_per_second": 4.317,
97
+ "eval_steps_per_second": 1.079,
98
+ "step": 60
99
+ },
100
+ {
101
+ "epoch": 2.92,
102
+ "learning_rate": 2.777777777777778e-06,
103
+ "loss": 0.855,
104
+ "step": 70
105
+ },
106
+ {
107
+ "epoch": 2.92,
108
+ "eval_accuracy": 0.5833333134651184,
109
+ "eval_loss": 0.9461669921875,
110
+ "eval_runtime": 9.9807,
111
+ "eval_samples_per_second": 4.809,
112
+ "eval_steps_per_second": 1.202,
113
+ "step": 70
114
+ }
115
+ ],
116
+ "max_steps": 72,
117
+ "num_train_epochs": 3,
118
+ "total_flos": 2.022508856471088e+17,
119
+ "trial_name": null,
120
+ "trial_params": null
121
+ }
preprocessor_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
- "processor_class": "Wav2Vec2ProcessorWithLM",
8
  "return_attention_mask": true,
9
- "sampling_rate": 16000
10
- }
 
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
 
7
  "return_attention_mask": true,
8
+ "sampling_rate": 16000,
9
+ "processor_class": "Wav2Vec2ProcessorWithLM"
10
+ }