Hugging Face's logo

QuanHcmus
/
wav2vec2-base-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
QuanHcmus commited on
Commit
9c71478
•
1 Parent(s): c0a4b47

Training in progress, epoch 0

Browse files
Files changed (8) hide show
  1. .gitignore +1 -0
  2. config.json +142 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. runs/Mar16_10-16-48_b97f8a86403a/events.out.tfevents.1710584270.b97f8a86403a.7710.0 +3 -0
  6. runs/Mar16_10-19-01_b97f8a86403a/events.out.tfevents.1710584346.b97f8a86403a.7710.1 +3 -0
  7. runs/Mar16_10-20-38_b97f8a86403a/events.out.tfevents.1710584442.b97f8a86403a.9784.0 +3 -0
  8. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
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_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "blues",
61
+ "1": "classical",
62
+ "2": "country",
63
+ "3": "disco",
64
+ "4": "hiphop",
65
+ "5": "jazz",
66
+ "6": "metal",
67
+ "7": "pop",
68
+ "8": "reggae",
69
+ "9": "rock"
70
+ },
71
+ "initializer_range": 0.02,
72
+ "intermediate_size": 3072,
73
+ "label2id": {
74
+ "blues": "0",
75
+ "classical": "1",
76
+ "country": "2",
77
+ "disco": "3",
78
+ "hiphop": "4",
79
+ "jazz": "5",
80
+ "metal": "6",
81
+ "pop": "7",
82
+ "reggae": "8",
83
+ "rock": "9"
84
+ },
85
+ "layer_norm_eps": 1e-05,
86
+ "layerdrop": 0.0,
87
+ "mask_channel_length": 10,
88
+ "mask_channel_min_space": 1,
89
+ "mask_channel_other": 0.0,
90
+ "mask_channel_prob": 0.0,
91
+ "mask_channel_selection": "static",
92
+ "mask_feature_length": 10,
93
+ "mask_feature_min_masks": 0,
94
+ "mask_feature_prob": 0.0,
95
+ "mask_time_length": 10,
96
+ "mask_time_min_masks": 2,
97
+ "mask_time_min_space": 1,
98
+ "mask_time_other": 0.0,
99
+ "mask_time_prob": 0.05,
100
+ "mask_time_selection": "static",
101
+ "model_type": "wav2vec2",
102
+ "no_mask_channel_overlap": false,
103
+ "no_mask_time_overlap": false,
104
+ "num_adapter_layers": 3,
105
+ "num_attention_heads": 12,
106
+ "num_codevector_groups": 2,
107
+ "num_codevectors_per_group": 320,
108
+ "num_conv_pos_embedding_groups": 16,
109
+ "num_conv_pos_embeddings": 128,
110
+ "num_feat_extract_layers": 7,
111
+ "num_hidden_layers": 12,
112
+ "num_negatives": 100,
113
+ "output_hidden_size": 768,
114
+ "pad_token_id": 0,
115
+ "proj_codevector_dim": 256,
116
+ "tdnn_dilation": [
117
+ 1,
118
+ 2,
119
+ 3,
120
+ 1,
121
+ 1
122
+ ],
123
+ "tdnn_dim": [
124
+ 512,
125
+ 512,
126
+ 512,
127
+ 512,
128
+ 1500
129
+ ],
130
+ "tdnn_kernel": [
131
+ 5,
132
+ 3,
133
+ 3,
134
+ 1,
135
+ 1
136
+ ],
137
+ "torch_dtype": "float32",
138
+ "transformers_version": "4.31.0",
139
+ "use_weighted_layer_sum": false,
140
+ "vocab_size": 32,
141
+ "xvector_output_dim": 512
142
+ }
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 sha256:31378449ad35158b220407db4607ef55ee6c640b5c6c9fb30112b10cf2557531
3
+ size 378359142
runs/Mar16_10-16-48_b97f8a86403a/events.out.tfevents.1710584270.b97f8a86403a.7710.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89e1d418a3d8faac503c1150113f014c75d102b65d55ef940a635610e62d41e
3
+ size 6198
runs/Mar16_10-19-01_b97f8a86403a/events.out.tfevents.1710584346.b97f8a86403a.7710.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e7b9b820ef5baaf4b71ba4b2b2f30d113e194c1694824d7c36dbf904debfac9
3
+ size 4184
runs/Mar16_10-20-38_b97f8a86403a/events.out.tfevents.1710584442.b97f8a86403a.9784.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f8c1a7c89e0ec7d8dd579df39fae13b8b3a949cd708b3248c6a81a3ced0a994
3
+ size 6821
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa094a7fc00e977323ce61f9732c789d971471fbf0c179df8c31d17bfad86af
3
+ size 4472