Hugging Face's logo

Jainam
/
audio_classify_v1

Audio Classification
Transformers
PyTorch
wav2vec2
Model card Files
xet
Community
1
Jainam commited on
Commit
1d12803
·
1 Parent(s): 98cef37

commit-v1

Browse files
Files changed (8) hide show
  1. config.json +127 -0
  2. optimizer.pt +3 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +109 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
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": "hindi_male",
60
+ "1": "gujarati_male",
61
+ "2": "tamil_male"
62
+ },
63
+ "initializer_range": 0.02,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "gujarati_male": "1",
67
+ "hindi_male": "0",
68
+ "tamil_male": "2"
69
+ },
70
+ "layer_norm_eps": 1e-05,
71
+ "layerdrop": 0.0,
72
+ "mask_channel_length": 10,
73
+ "mask_channel_min_space": 1,
74
+ "mask_channel_other": 0.0,
75
+ "mask_channel_prob": 0.0,
76
+ "mask_channel_selection": "static",
77
+ "mask_feature_length": 10,
78
+ "mask_feature_min_masks": 0,
79
+ "mask_feature_prob": 0.0,
80
+ "mask_time_length": 10,
81
+ "mask_time_min_masks": 2,
82
+ "mask_time_min_space": 1,
83
+ "mask_time_other": 0.0,
84
+ "mask_time_prob": 0.05,
85
+ "mask_time_selection": "static",
86
+ "model_type": "wav2vec2",
87
+ "no_mask_channel_overlap": false,
88
+ "no_mask_time_overlap": false,
89
+ "num_adapter_layers": 3,
90
+ "num_attention_heads": 12,
91
+ "num_codevector_groups": 2,
92
+ "num_codevectors_per_group": 320,
93
+ "num_conv_pos_embedding_groups": 16,
94
+ "num_conv_pos_embeddings": 128,
95
+ "num_feat_extract_layers": 7,
96
+ "num_hidden_layers": 12,
97
+ "num_negatives": 100,
98
+ "output_hidden_size": 768,
99
+ "pad_token_id": 0,
100
+ "proj_codevector_dim": 256,
101
+ "tdnn_dilation": [
102
+ 1,
103
+ 2,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "tdnn_dim": [
109
+ 512,
110
+ 512,
111
+ 512,
112
+ 512,
113
+ 1500
114
+ ],
115
+ "tdnn_kernel": [
116
+ 5,
117
+ 3,
118
+ 3,
119
+ 1,
120
+ 1
121
+ ],
122
+ "torch_dtype": "float32",
123
+ "transformers_version": "4.26.1",
124
+ "use_weighted_layer_sum": false,
125
+ "vocab_size": 32,
126
+ "xvector_output_dim": 512
127
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3371989030375b9a919160065b718c475cb76bb4441f3c9b16175b3343133a1b
3
+ size 756674757
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a67309940b81f4bc1629d9919e728e68621c7d8e9eb7d610b699c978ddf31d
3
+ size 378348457
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fbe099289a035b87248f04bb429c08df388dafdea9a64c79f05a3b7e4589aaf
3
+ size 13553
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d5a61d6c16ff2b5d01a1e84e50dfcec12e2ea5f64272f34657e1c428037135
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9946043165467626,
3
+ "best_model_checkpoint": "audio_classify_v1/checkpoint-85",
4
+ "epoch": 4.9855072463768115,
5
+ "global_step": 85,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.58,
12
+ "learning_rate": 2.9605263157894735e-05,
13
+ "loss": 0.1898,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.99,
18
+ "eval_accuracy": 0.9892086330935251,
19
+ "eval_loss": 0.13191261887550354,
20
+ "eval_runtime": 40.5603,
21
+ "eval_samples_per_second": 13.708,
22
+ "eval_steps_per_second": 0.444,
23
+ "step": 17
24
+ },
25
+ {
26
+ "epoch": 1.17,
27
+ "learning_rate": 2.5657894736842107e-05,
28
+ "loss": 0.1711,
29
+ "step": 20
30
+ },
31
+ {
32
+ "epoch": 1.75,
33
+ "learning_rate": 2.1710526315789474e-05,
34
+ "loss": 0.1198,
35
+ "step": 30
36
+ },
37
+ {
38
+ "epoch": 1.99,
39
+ "eval_accuracy": 0.9856115107913669,
40
+ "eval_loss": 0.10289730876684189,
41
+ "eval_runtime": 41.2389,
42
+ "eval_samples_per_second": 13.482,
43
+ "eval_steps_per_second": 0.436,
44
+ "step": 34
45
+ },
46
+ {
47
+ "epoch": 2.35,
48
+ "learning_rate": 1.7763157894736842e-05,
49
+ "loss": 0.1009,
50
+ "step": 40
51
+ },
52
+ {
53
+ "epoch": 2.93,
54
+ "learning_rate": 1.3815789473684211e-05,
55
+ "loss": 0.0801,
56
+ "step": 50
57
+ },
58
+ {
59
+ "epoch": 2.99,
60
+ "eval_accuracy": 0.987410071942446,
61
+ "eval_loss": 0.09273109585046768,
62
+ "eval_runtime": 41.4271,
63
+ "eval_samples_per_second": 13.421,
64
+ "eval_steps_per_second": 0.434,
65
+ "step": 51
66
+ },
67
+ {
68
+ "epoch": 3.52,
69
+ "learning_rate": 9.868421052631579e-06,
70
+ "loss": 0.0791,
71
+ "step": 60
72
+ },
73
+ {
74
+ "epoch": 3.99,
75
+ "eval_accuracy": 0.9910071942446043,
76
+ "eval_loss": 0.06818023324012756,
77
+ "eval_runtime": 44.7553,
78
+ "eval_samples_per_second": 12.423,
79
+ "eval_steps_per_second": 0.402,
80
+ "step": 68
81
+ },
82
+ {
83
+ "epoch": 4.12,
84
+ "learning_rate": 5.921052631578948e-06,
85
+ "loss": 0.0679,
86
+ "step": 70
87
+ },
88
+ {
89
+ "epoch": 4.7,
90
+ "learning_rate": 1.9736842105263157e-06,
91
+ "loss": 0.0618,
92
+ "step": 80
93
+ },
94
+ {
95
+ "epoch": 4.99,
96
+ "eval_accuracy": 0.9946043165467626,
97
+ "eval_loss": 0.06044043228030205,
98
+ "eval_runtime": 45.6171,
99
+ "eval_samples_per_second": 12.188,
100
+ "eval_steps_per_second": 0.395,
101
+ "step": 85
102
+ }
103
+ ],
104
+ "max_steps": 85,
105
+ "num_train_epochs": 5,
106
+ "total_flos": 9.968365728576e+16,
107
+ "trial_name": null,
108
+ "trial_params": null
109
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd981068cd9494cbfb6fdd059eb72698933215868b9d4a978f9f1aac515e1c67
3
+ size 3515