devashish-bhake commited on
Commit
01db40d
·
1 Parent(s): c112a84

modified: SER_model/config.json

Browse files

modified: SER_model/preprocessor_config.json
modified: SER_model/pytorch_model.bin
modified: SER_model/training_args.bin

SER_model/config.json CHANGED
@@ -1,134 +1,132 @@
1
  {
2
- "_name_or_path": "./SPT_model",
3
- "activation_dropout": 0.0,
4
- "adapter_kernel_size": 3,
5
- "adapter_stride": 2,
6
- "add_adapter": false,
7
- "apply_spec_augment": true,
8
- "architectures": [
9
- "Wav2Vec2ForSequenceClassification"
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": false,
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": "sum",
45
- "ctc_zero_infinity": false,
46
- "diversity_loss_weight": 0.1,
47
- "do_stable_layer_norm": false,
48
- "eos_token_id": 2,
49
- "feat_extract_activation": "gelu",
50
- "feat_extract_norm": "group",
51
- "feat_proj_dropout": 0.1,
52
- "feat_quantizer_dropout": 0.0,
53
- "final_dropout": 0.0,
54
- "freeze_feat_extract_train": true,
55
- "hidden_act": "gelu",
56
- "hidden_dropout": 0.1,
57
- "hidden_size": 768,
58
- "id2label": {
59
- "0": "angry",
60
- "1": "disgust",
61
- "2": "fear",
62
- "3": "happy",
63
- "4": "neutral",
64
- "5": "sad"
65
- },
66
- "initializer_range": 0.02,
67
- "intermediate_size": 3072,
68
- "label2id": {
69
- "angry": "0",
70
- "disgust": "1",
71
- "fear": "2",
72
- "happy": "3",
73
- "neutral": "4",
74
- "sad": "5"
75
- },
76
- "layer_norm_eps": 1e-05,
77
- "layerdrop": 0.0,
78
- "mask_channel_length": 10,
79
- "mask_channel_min_space": 1,
80
- "mask_channel_other": 0.0,
81
- "mask_channel_prob": 0.0,
82
- "mask_channel_selection": "static",
83
- "mask_feature_length": 10,
84
- "mask_feature_min_masks": 0,
85
- "mask_feature_prob": 0.0,
86
- "mask_time_length": 10,
87
- "mask_time_min_masks": 2,
88
- "mask_time_min_space": 1,
89
- "mask_time_other": 0.0,
90
- "mask_time_prob": 0.05,
91
- "mask_time_selection": "static",
92
- "model_type": "wav2vec2",
93
- "no_mask_channel_overlap": false,
94
- "no_mask_time_overlap": false,
95
- "num_adapter_layers": 3,
96
- "num_attention_heads": 12,
97
- "num_codevector_groups": 2,
98
- "num_codevectors_per_group": 320,
99
- "num_conv_pos_embedding_groups": 16,
100
- "num_conv_pos_embeddings": 128,
101
- "num_feat_extract_layers": 7,
102
- "num_hidden_layers": 12,
103
- "num_negatives": 100,
104
- "output_hidden_size": 768,
105
- "pad_token_id": 0,
106
- "proj_codevector_dim": 256,
107
- "tdnn_dilation": [
108
- 1,
109
- 2,
110
- 3,
111
- 1,
112
- 1
113
- ],
114
- "tdnn_dim": [
115
- 512,
116
- 512,
117
- 512,
118
- 512,
119
- 1500
120
- ],
121
- "tdnn_kernel": [
122
- 5,
123
- 3,
124
- 3,
125
- 1,
126
- 1
127
- ],
128
- "torch_dtype": "float32",
129
- "transformers_version": "4.25.1",
130
- "use_weighted_layer_sum": false,
131
- "vocab_size": 32,
132
- "xvector_output_dim": 512
133
- }
134
-
 
1
  {
2
+ "_name_or_path": "harshit345/xlsr-wav2vec-speech-emotion-recognition",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
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": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "finetuning_task": "wav2vec2_clf",
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 1024,
59
+ "id2label": {
60
+ "0": "anger",
61
+ "1": "disgust",
62
+ "2": "fear",
63
+ "3": "happiness",
64
+ "4": "sadness"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 4096,
68
+ "label2id": {
69
+ "anger": 0,
70
+ "disgust": 1,
71
+ "fear": 2,
72
+ "happiness": 3,
73
+ "sadness": 4
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "layerdrop": 0.1,
77
+ "mask_channel_length": 10,
78
+ "mask_channel_min_space": 1,
79
+ "mask_channel_other": 0.0,
80
+ "mask_channel_prob": 0.0,
81
+ "mask_channel_selection": "static",
82
+ "mask_feature_length": 10,
83
+ "mask_feature_min_masks": 0,
84
+ "mask_feature_prob": 0.0,
85
+ "mask_time_length": 10,
86
+ "mask_time_min_masks": 2,
87
+ "mask_time_min_space": 1,
88
+ "mask_time_other": 0.0,
89
+ "mask_time_prob": 0.05,
90
+ "mask_time_selection": "static",
91
+ "model_type": "wav2vec2",
92
+ "num_adapter_layers": 3,
93
+ "num_attention_heads": 16,
94
+ "num_codevector_groups": 2,
95
+ "num_codevectors_per_group": 320,
96
+ "num_conv_pos_embedding_groups": 16,
97
+ "num_conv_pos_embeddings": 128,
98
+ "num_feat_extract_layers": 7,
99
+ "num_hidden_layers": 24,
100
+ "num_negatives": 100,
101
+ "output_hidden_size": 1024,
102
+ "pad_token_id": 54,
103
+ "pooling_mode": "mean",
104
+ "problem_type": "single_label_classification",
105
+ "proj_codevector_dim": 256,
106
+ "tdnn_dilation": [
107
+ 1,
108
+ 2,
109
+ 3,
110
+ 1,
111
+ 1
112
+ ],
113
+ "tdnn_dim": [
114
+ 512,
115
+ 512,
116
+ 512,
117
+ 512,
118
+ 1500
119
+ ],
120
+ "tdnn_kernel": [
121
+ 5,
122
+ 3,
123
+ 3,
124
+ 1,
125
+ 1
126
+ ],
127
+ "torch_dtype": "float32",
128
+ "transformers_version": "4.18.0",
129
+ "use_weighted_layer_sum": false,
130
+ "vocab_size": 55,
131
+ "xvector_output_dim": 512
132
+ }
 
 
SER_model/preprocessor_config.json CHANGED
@@ -1,9 +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
- }
 
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
+ }
SER_model/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:583aea2bf31f8713200e46bd9f1c6735beed40b5ec0d1f6e2decd45c6446e1b6
3
- size 378352659
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f15f40f02086b67ac11d9a0d86ea0543e566b4b5ea68ebe40727039ba10283
3
+ size 1262954093
SER_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c08295d554ee360c4ed5b8090035b4384199468399ca15720321255bf7bf7b3
3
- size 3503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831905a10c8c6e96d743a653765f1b83c8f209b13341540da2ef34e8b0263a13
3
+ size 3119