Hugging Face's logo

f0ghedgeh0g
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
f0ghedgeh0g commited on
Commit
887b44a
·
verified ·
1 Parent(s): 7ab11b0

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +97 -96
  2. model.safetensors +1 -1
  3. preprocessor_config.json +9 -9
  4. training_args.bin +2 -2
config.json CHANGED
@@ -1,96 +1,97 @@
1
- {
2
- "_name_or_path": "ntu-spml/distilhubert",
3
- "activation_dropout": 0.1,
4
- "apply_spec_augment": false,
5
- "architectures": [
6
- "HubertForSequenceClassification"
7
- ],
8
- "attention_dropout": 0.1,
9
- "bos_token_id": 1,
10
- "classifier_proj_size": 256,
11
- "conv_bias": false,
12
- "conv_dim": [
13
- 512,
14
- 512,
15
- 512,
16
- 512,
17
- 512,
18
- 512,
19
- 512
20
- ],
21
- "conv_kernel": [
22
- 10,
23
- 3,
24
- 3,
25
- 3,
26
- 3,
27
- 2,
28
- 2
29
- ],
30
- "conv_stride": [
31
- 5,
32
- 2,
33
- 2,
34
- 2,
35
- 2,
36
- 2,
37
- 2
38
- ],
39
- "ctc_loss_reduction": "sum",
40
- "ctc_zero_infinity": false,
41
- "do_stable_layer_norm": false,
42
- "eos_token_id": 2,
43
- "feat_extract_activation": "gelu",
44
- "feat_extract_norm": "group",
45
- "feat_proj_dropout": 0.0,
46
- "feat_proj_layer_norm": false,
47
- "final_dropout": 0.1,
48
- "hidden_act": "gelu",
49
- "hidden_dropout": 0.2,
50
- "hidden_size": 768,
51
- "id2label": {
52
- "0": "blues",
53
- "1": "classical",
54
- "2": "country",
55
- "3": "disco",
56
- "4": "hiphop",
57
- "5": "jazz",
58
- "6": "metal",
59
- "7": "pop",
60
- "8": "reggae",
61
- "9": "rock"
62
- },
63
- "initializer_range": 0.02,
64
- "intermediate_size": 3072,
65
- "label2id": {
66
- "blues": "0",
67
- "classical": "1",
68
- "country": "2",
69
- "disco": "3",
70
- "hiphop": "4",
71
- "jazz": "5",
72
- "metal": "6",
73
- "pop": "7",
74
- "reggae": "8",
75
- "rock": "9"
76
- },
77
- "layer_norm_eps": 1e-05,
78
- "layerdrop": 0.1,
79
- "mask_feature_length": 10,
80
- "mask_feature_min_masks": 0,
81
- "mask_feature_prob": 0.0,
82
- "mask_time_length": 10,
83
- "mask_time_min_masks": 2,
84
- "mask_time_prob": 0.05,
85
- "model_type": "hubert",
86
- "num_attention_heads": 12,
87
- "num_conv_pos_embedding_groups": 16,
88
- "num_conv_pos_embeddings": 128,
89
- "num_feat_extract_layers": 7,
90
- "num_hidden_layers": 2,
91
- "pad_token_id": 0,
92
- "torch_dtype": "float32",
93
- "transformers_version": "4.47.1",
94
- "use_weighted_layer_sum": false,
95
- "vocab_size": 32
96
- }
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_pos_batch_norm": false,
31
+ "conv_stride": [
32
+ 5,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2
39
+ ],
40
+ "ctc_loss_reduction": "sum",
41
+ "ctc_zero_infinity": false,
42
+ "do_stable_layer_norm": false,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_norm": "group",
46
+ "feat_proj_dropout": 0.0,
47
+ "feat_proj_layer_norm": false,
48
+ "final_dropout": 0.1,
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.2,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "blues",
54
+ "1": "classical",
55
+ "2": "country",
56
+ "3": "disco",
57
+ "4": "hiphop",
58
+ "5": "jazz",
59
+ "6": "metal",
60
+ "7": "pop",
61
+ "8": "reggae",
62
+ "9": "rock"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "label2id": {
67
+ "blues": "0",
68
+ "classical": "1",
69
+ "country": "2",
70
+ "disco": "3",
71
+ "hiphop": "4",
72
+ "jazz": "5",
73
+ "metal": "6",
74
+ "pop": "7",
75
+ "reggae": "8",
76
+ "rock": "9"
77
+ },
78
+ "layer_norm_eps": 1e-05,
79
+ "layerdrop": 0.1,
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_prob": 0.05,
86
+ "model_type": "hubert",
87
+ "num_attention_heads": 12,
88
+ "num_conv_pos_embedding_groups": 16,
89
+ "num_conv_pos_embeddings": 128,
90
+ "num_feat_extract_layers": 7,
91
+ "num_hidden_layers": 2,
92
+ "pad_token_id": 0,
93
+ "torch_dtype": "float32",
94
+ "transformers_version": "4.48.0.dev0",
95
+ "use_weighted_layer_sum": false,
96
+ "vocab_size": 32
97
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54cbe27b8feb63081ef9328a7abb1751687f356b88877d1f55e61f86b03a7546
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478547e4d231f86c28d934e90759014cf86f0c8d394369249234be038f173065
3
  size 94771728
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,
7
- "return_attention_mask": true,
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,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e55610acb04c5f1a200ae83f3acb03da8c5039c41ab4570d18a964858e27b9a
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed5b134ab42dbbb591baa5f3aea954af3a1e0e3b144a4ccff15cdabbe42fa848
3
+ size 5304