Hugging Face's logo

dima806
/
music_genres_classification

Audio Classification
Transformers
PyTorch
Safetensors
wav2vec2
Inference Endpoints
Model card Files Community
1
dima806 commited on
Commit
18493b9
•
1 Parent(s): 69f13e6

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-2600/config.json +133 -0
  2. checkpoint-2600/optimizer.pt +3 -0
  3. checkpoint-2600/preprocessor_config.json +9 -0
  4. checkpoint-2600/pytorch_model.bin +3 -0
  5. checkpoint-2600/rng_state.pth +3 -0
  6. checkpoint-2600/scheduler.pt +3 -0
  7. checkpoint-2600/trainer_state.json +0 -0
  8. checkpoint-2600/training_args.bin +3 -0
  9. config.json +133 -0
  10. preprocessor_config.json +9 -0
  11. pytorch_model.bin +3 -0
  12. training_args.bin +3 -0
checkpoint-2600/config.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "disco",
62
+ "1": "metal",
63
+ "2": "reggae",
64
+ "3": "blues",
65
+ "4": "rock",
66
+ "5": "classical",
67
+ "6": "jazz",
68
+ "7": "hiphop",
69
+ "8": "country",
70
+ "9": "pop"
71
+ },
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 3072,
74
+ "label2id": {
75
+ "LABEL_0": 0,
76
+ "LABEL_1": 1,
77
+ "LABEL_2": 2,
78
+ "LABEL_3": 3,
79
+ "LABEL_4": 4,
80
+ "LABEL_5": 5,
81
+ "LABEL_6": 6,
82
+ "LABEL_7": 7,
83
+ "LABEL_8": 8,
84
+ "LABEL_9": 9
85
+ },
86
+ "layer_norm_eps": 1e-05,
87
+ "layerdrop": 0.1,
88
+ "mask_feature_length": 10,
89
+ "mask_feature_min_masks": 0,
90
+ "mask_feature_prob": 0.0,
91
+ "mask_time_length": 10,
92
+ "mask_time_min_masks": 2,
93
+ "mask_time_prob": 0.05,
94
+ "model_type": "wav2vec2",
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": "4.28.1",
130
+ "use_weighted_layer_sum": false,
131
+ "vocab_size": 32,
132
+ "xvector_output_dim": 512
133
+ }
checkpoint-2600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61fcf11147113719f56fe8642b5dd69e8d81f891624140301dec22c169b2660
3
+ size 756693861
checkpoint-2600/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-2600/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dffd204848cfb67bb32816081ea6a0b3534c2d1800059a7d649faac401cab52
3
+ size 378356755
checkpoint-2600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:230272e2a96f121cc06d9e4e8c78298d860fa8ff7c9738dfa724b24d88507d71
3
+ size 14567
checkpoint-2600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e211968cdaaa810ce576a66dac486f9ba721ead354686231be925a617841b1
3
+ size 623
checkpoint-2600/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f6d3e63d4de719bb36d7548c253806efc3940781ad431c3a151376dada1efed
3
+ size 3567
config.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "disco",
62
+ "1": "metal",
63
+ "2": "reggae",
64
+ "3": "blues",
65
+ "4": "rock",
66
+ "5": "classical",
67
+ "6": "jazz",
68
+ "7": "hiphop",
69
+ "8": "country",
70
+ "9": "pop"
71
+ },
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 3072,
74
+ "label2id": {
75
+ "LABEL_0": 0,
76
+ "LABEL_1": 1,
77
+ "LABEL_2": 2,
78
+ "LABEL_3": 3,
79
+ "LABEL_4": 4,
80
+ "LABEL_5": 5,
81
+ "LABEL_6": 6,
82
+ "LABEL_7": 7,
83
+ "LABEL_8": 8,
84
+ "LABEL_9": 9
85
+ },
86
+ "layer_norm_eps": 1e-05,
87
+ "layerdrop": 0.1,
88
+ "mask_feature_length": 10,
89
+ "mask_feature_min_masks": 0,
90
+ "mask_feature_prob": 0.0,
91
+ "mask_time_length": 10,
92
+ "mask_time_min_masks": 2,
93
+ "mask_time_prob": 0.05,
94
+ "model_type": "wav2vec2",
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": "4.28.1",
130
+ "use_weighted_layer_sum": false,
131
+ "vocab_size": 32,
132
+ "xvector_output_dim": 512
133
+ }
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 sha256:5dffd204848cfb67bb32816081ea6a0b3534c2d1800059a7d649faac401cab52
3
+ size 378356755
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f6d3e63d4de719bb36d7548c253806efc3940781ad431c3a151376dada1efed
3
+ size 3567