Hugging Face's logo

Bhaveen
/
Musical-Instrument-Classification

Audio Classification
Transformers
PyTorch
Safetensors
English
wav2vec2
audio
musical-instruments
Eval Results
Model card Files
xet
Community
1
Bhaveen commited on
Commit
cc57f82
·
verified ·
1 Parent(s): 89d9343

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-1800/config.json +131 -0
  2. checkpoint-1800/optimizer.pt +3 -0
  3. checkpoint-1800/preprocessor_config.json +9 -0
  4. checkpoint-1800/pytorch_model.bin +3 -0
  5. checkpoint-1800/rng_state.pth +3 -0
  6. checkpoint-1800/scheduler.pt +3 -0
  7. checkpoint-1800/trainer_state.json +0 -0
  8. checkpoint-1800/training_args.bin +3 -0
  9. config.json +131 -0
  10. preprocessor_config.json +9 -0
  11. pytorch_model.bin +3 -0
  12. training_args.bin +3 -0
checkpoint-1800/config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Acoustic_Guitar",
62
+ "1": "Bass_Guitar",
63
+ "2": "Drum_set",
64
+ "3": "Electro_Guitar",
65
+ "4": "flute",
66
+ "5": "Hi_Hats",
67
+ "6": "Keyboard",
68
+ "7": "Trumpet",
69
+ "8": "Violin"
70
+ },
71
+ "initializer_range": 0.02,
72
+ "intermediate_size": 3072,
73
+ "label2id": {
74
+ "LABEL_0": 0,
75
+ "LABEL_1": 1,
76
+ "LABEL_2": 2,
77
+ "LABEL_3": 3,
78
+ "LABEL_4": 4,
79
+ "LABEL_5": 5,
80
+ "LABEL_6": 6,
81
+ "LABEL_7": 7,
82
+ "LABEL_8": 8
83
+ },
84
+ "layer_norm_eps": 1e-05,
85
+ "layerdrop": 0.1,
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_prob": 0.05,
92
+ "model_type": "wav2vec2",
93
+ "num_adapter_layers": 3,
94
+ "num_attention_heads": 12,
95
+ "num_codevector_groups": 2,
96
+ "num_codevectors_per_group": 320,
97
+ "num_conv_pos_embedding_groups": 16,
98
+ "num_conv_pos_embeddings": 128,
99
+ "num_feat_extract_layers": 7,
100
+ "num_hidden_layers": 12,
101
+ "num_negatives": 100,
102
+ "output_hidden_size": 768,
103
+ "pad_token_id": 0,
104
+ "proj_codevector_dim": 256,
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": "4.28.1",
128
+ "use_weighted_layer_sum": false,
129
+ "vocab_size": 32,
130
+ "xvector_output_dim": 512
131
+ }
checkpoint-1800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e1ff16f8596c408cb2dc7e1aad24943cf8bf35a37410ce3888cd322c558f64
3
+ size 756693690
checkpoint-1800/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
+ }
checkpoint-1800/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4099e176de4c47fe93a1e225e91d8a67cfba132a907fd97e017bf86dd34ccc5
3
+ size 378358054
checkpoint-1800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c64e8b9a820ffe430d4ec63b38e104846f7124988cc942101c8337287bd4a4
3
+ size 14308
checkpoint-1800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb483a8e7dd5355fed20928eab72aeae44d85edb6fe3657395ddb2a2378d0f4
3
+ size 1064
checkpoint-1800/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4bc8d51167f68712e533a940025e3b1448d389451dcbbef874afb56f62835b
3
+ size 4024
config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Acoustic_Guitar",
62
+ "1": "Bass_Guitar",
63
+ "2": "Drum_set",
64
+ "3": "Electro_Guitar",
65
+ "4": "flute",
66
+ "5": "Hi_Hats",
67
+ "6": "Keyboard",
68
+ "7": "Trumpet",
69
+ "8": "Violin"
70
+ },
71
+ "initializer_range": 0.02,
72
+ "intermediate_size": 3072,
73
+ "label2id": {
74
+ "LABEL_0": 0,
75
+ "LABEL_1": 1,
76
+ "LABEL_2": 2,
77
+ "LABEL_3": 3,
78
+ "LABEL_4": 4,
79
+ "LABEL_5": 5,
80
+ "LABEL_6": 6,
81
+ "LABEL_7": 7,
82
+ "LABEL_8": 8
83
+ },
84
+ "layer_norm_eps": 1e-05,
85
+ "layerdrop": 0.1,
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_prob": 0.05,
92
+ "model_type": "wav2vec2",
93
+ "num_adapter_layers": 3,
94
+ "num_attention_heads": 12,
95
+ "num_codevector_groups": 2,
96
+ "num_codevectors_per_group": 320,
97
+ "num_conv_pos_embedding_groups": 16,
98
+ "num_conv_pos_embeddings": 128,
99
+ "num_feat_extract_layers": 7,
100
+ "num_hidden_layers": 12,
101
+ "num_negatives": 100,
102
+ "output_hidden_size": 768,
103
+ "pad_token_id": 0,
104
+ "proj_codevector_dim": 256,
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": "4.28.1",
128
+ "use_weighted_layer_sum": false,
129
+ "vocab_size": 32,
130
+ "xvector_output_dim": 512
131
+ }
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:a4099e176de4c47fe93a1e225e91d8a67cfba132a907fd97e017bf86dd34ccc5
3
+ size 378358054
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4bc8d51167f68712e533a940025e3b1448d389451dcbbef874afb56f62835b
3
+ size 4024