Hugging Face's logo

timothy-geiger
/
music_genres_classification-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Inference Endpoints
Model card Files Metrics Community
timothy-geiger commited on
Commit
4cc27dd
•
1 Parent(s): f070c15

Training in progress, epoch 2

Browse files
Files changed (7) hide show
  1. config.json +134 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +9 -0
  4. runs/Mar07_11-44-37_b7f6c57d4117/events.out.tfevents.1709811879.b7f6c57d4117.546.0 +3 -0
  5. runs/Mar07_11-50-03_b7f6c57d4117/events.out.tfevents.1709812207.b7f6c57d4117.546.1 +3 -0
  6. runs/Mar07_11-50-03_b7f6c57d4117/events.out.tfevents.1709812266.b7f6c57d4117.546.2 +3 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dima806/music_genres_classification",
3
+ "activation_dropout": 0.1,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "id2label": {
62
+ "0": "blues",
63
+ "1": "classical",
64
+ "2": "country",
65
+ "3": "disco",
66
+ "4": "hiphop",
67
+ "5": "jazz",
68
+ "6": "metal",
69
+ "7": "pop",
70
+ "8": "reggae",
71
+ "9": "rock"
72
+ },
73
+ "initializer_range": 0.02,
74
+ "intermediate_size": 3072,
75
+ "label2id": {
76
+ "blues": "0",
77
+ "classical": "1",
78
+ "country": "2",
79
+ "disco": "3",
80
+ "hiphop": "4",
81
+ "jazz": "5",
82
+ "metal": "6",
83
+ "pop": "7",
84
+ "reggae": "8",
85
+ "rock": "9"
86
+ },
87
+ "layer_norm_eps": 1e-05,
88
+ "layerdrop": 0.1,
89
+ "mask_feature_length": 10,
90
+ "mask_feature_min_masks": 0,
91
+ "mask_feature_prob": 0.0,
92
+ "mask_time_length": 10,
93
+ "mask_time_min_masks": 2,
94
+ "mask_time_prob": 0.05,
95
+ "model_type": "wav2vec2",
96
+ "num_adapter_layers": 3,
97
+ "num_attention_heads": 12,
98
+ "num_codevector_groups": 2,
99
+ "num_codevectors_per_group": 320,
100
+ "num_conv_pos_embedding_groups": 16,
101
+ "num_conv_pos_embeddings": 128,
102
+ "num_feat_extract_layers": 7,
103
+ "num_hidden_layers": 12,
104
+ "num_negatives": 100,
105
+ "output_hidden_size": 768,
106
+ "pad_token_id": 0,
107
+ "proj_codevector_dim": 256,
108
+ "tdnn_dilation": [
109
+ 1,
110
+ 2,
111
+ 3,
112
+ 1,
113
+ 1
114
+ ],
115
+ "tdnn_dim": [
116
+ 512,
117
+ 512,
118
+ 512,
119
+ 512,
120
+ 1500
121
+ ],
122
+ "tdnn_kernel": [
123
+ 5,
124
+ 3,
125
+ 3,
126
+ 1,
127
+ 1
128
+ ],
129
+ "torch_dtype": "float32",
130
+ "transformers_version": "4.38.2",
131
+ "use_weighted_layer_sum": false,
132
+ "vocab_size": 32,
133
+ "xvector_output_dim": 512
134
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b590160466b509bf0dfc0cf327ea2aa52614babce0634b4dfa7744f8167130
3
+ size 378310592
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": true,
8
+ "sampling_rate": 16000
9
+ }
runs/Mar07_11-44-37_b7f6c57d4117/events.out.tfevents.1709811879.b7f6c57d4117.546.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91d07c855a3ccdec1ec4eaee35a7af53e0c841cf96e46aedf56cd54f20bddba
3
+ size 6552
runs/Mar07_11-50-03_b7f6c57d4117/events.out.tfevents.1709812207.b7f6c57d4117.546.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:918648491edc67e0e35c78b9fbf8abfdce27158d62976bdc2fd97f6b1f58385b
3
+ size 6552
runs/Mar07_11-50-03_b7f6c57d4117/events.out.tfevents.1709812266.b7f6c57d4117.546.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52747f63ec413713759a8936917bf38bf8f5b89cc9909108157dddeb73316742
3
+ size 16587
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc099f573c044576df8a2272481d0fc2f261df06ae2cd80a18972b108aeb26c
3
+ size 4984