Hugging Face's logo

motheecreator
/
wav2vec2-base-finetuned-ks

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
motheecreator commited on
Commit
4cb8f58
•
1 Parent(s): 75364de

End of training

Browse files
Files changed (16) hide show
  1. README.md +82 -0
  2. config.json +126 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/Apr16_16-45-02_6858365b40e2/events.out.tfevents.1713286564.6858365b40e2.34.0 +3 -0
  6. runs/Apr16_17-11-47_6858365b40e2/events.out.tfevents.1713287508.6858365b40e2.370.0 +3 -0
  7. runs/Apr16_18-22-28_7a868e312e3d/events.out.tfevents.1713291821.7a868e312e3d.84.0 +3 -0
  8. runs/Apr16_18-41-46_7a868e312e3d/events.out.tfevents.1713292925.7a868e312e3d.394.0 +3 -0
  9. runs/Apr16_19-14-36_7a868e312e3d/events.out.tfevents.1713295090.7a868e312e3d.702.0 +3 -0
  10. runs/Apr16_19-39-25_ccd0e5f89ee3/events.out.tfevents.1713296786.ccd0e5f89ee3.34.0 +3 -0
  11. runs/Apr16_20-10-45_ccd0e5f89ee3/events.out.tfevents.1713298247.ccd0e5f89ee3.385.0 +3 -0
  12. runs/Apr16_21-42-23_ba1b200fa8ac/events.out.tfevents.1713304105.ba1b200fa8ac.82.0 +3 -0
  13. runs/Apr16_22-34-57_5439874391db/events.out.tfevents.1713306905.5439874391db.86.0 +3 -0
  14. runs/Apr16_22-39-06_5439874391db/events.out.tfevents.1713307152.5439874391db.86.1 +3 -0
  15. runs/Apr16_22-39-06_5439874391db/events.out.tfevents.1713330526.5439874391db.86.2 +3 -0
  16. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - audiofolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: wav2vec2-base-finetuned-ks
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: audiofolder
18
+ type: audiofolder
19
+ config: default
20
+ split: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9994443415447305
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # wav2vec2-base-finetuned-ks
32
+
33
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.0031
36
+ - Accuracy: 0.9994
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 3e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 5
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.0085 | 1.0 | 421 | 0.0133 | 0.9977 |
71
+ | 0.0005 | 2.0 | 842 | 0.0060 | 0.9986 |
72
+ | 0.0002 | 3.0 | 1263 | 0.0031 | 0.9994 |
73
+ | 0.0002 | 4.0 | 1684 | 0.0033 | 0.9993 |
74
+ | 0.0001 | 5.0 | 2105 | 0.0028 | 0.9994 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.39.3
80
+ - Pytorch 2.1.2
81
+ - Datasets 2.18.0
82
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "fake",
61
+ "1": "real"
62
+ },
63
+ "initializer_range": 0.02,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "fake": "0",
67
+ "real": "1"
68
+ },
69
+ "layer_norm_eps": 1e-05,
70
+ "layerdrop": 0.0,
71
+ "mask_channel_length": 10,
72
+ "mask_channel_min_space": 1,
73
+ "mask_channel_other": 0.0,
74
+ "mask_channel_prob": 0.0,
75
+ "mask_channel_selection": "static",
76
+ "mask_feature_length": 10,
77
+ "mask_feature_min_masks": 0,
78
+ "mask_feature_prob": 0.0,
79
+ "mask_time_length": 10,
80
+ "mask_time_min_masks": 2,
81
+ "mask_time_min_space": 1,
82
+ "mask_time_other": 0.0,
83
+ "mask_time_prob": 0.05,
84
+ "mask_time_selection": "static",
85
+ "model_type": "wav2vec2",
86
+ "no_mask_channel_overlap": false,
87
+ "no_mask_time_overlap": false,
88
+ "num_adapter_layers": 3,
89
+ "num_attention_heads": 12,
90
+ "num_codevector_groups": 2,
91
+ "num_codevectors_per_group": 320,
92
+ "num_conv_pos_embedding_groups": 16,
93
+ "num_conv_pos_embeddings": 128,
94
+ "num_feat_extract_layers": 7,
95
+ "num_hidden_layers": 12,
96
+ "num_negatives": 100,
97
+ "output_hidden_size": 768,
98
+ "pad_token_id": 0,
99
+ "proj_codevector_dim": 256,
100
+ "tdnn_dilation": [
101
+ 1,
102
+ 2,
103
+ 3,
104
+ 1,
105
+ 1
106
+ ],
107
+ "tdnn_dim": [
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 512,
112
+ 1500
113
+ ],
114
+ "tdnn_kernel": [
115
+ 5,
116
+ 3,
117
+ 3,
118
+ 1,
119
+ 1
120
+ ],
121
+ "torch_dtype": "float32",
122
+ "transformers_version": "4.39.3",
123
+ "use_weighted_layer_sum": false,
124
+ "vocab_size": 32,
125
+ "xvector_output_dim": 512
126
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405e6b51874ae7922050ef0918ffbd86188bebb3801283bdd8141ff9331e2fe8
3
+ size 378302360
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
+ }
runs/Apr16_16-45-02_6858365b40e2/events.out.tfevents.1713286564.6858365b40e2.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd4bdf0a8e50479145a5c1de21955f882edf69774fa9a2eaced847601aa00cc
3
+ size 4184
runs/Apr16_17-11-47_6858365b40e2/events.out.tfevents.1713287508.6858365b40e2.370.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb3bb2dd64d7af7d33c2d76388db2c2e91a818b1dfcf86700b68afe96d239c5b
3
+ size 4184
runs/Apr16_18-22-28_7a868e312e3d/events.out.tfevents.1713291821.7a868e312e3d.84.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5b3b354907f007655378704a5b9faf8d2ab1f240315d69842011e884ef7e1b
3
+ size 4184
runs/Apr16_18-41-46_7a868e312e3d/events.out.tfevents.1713292925.7a868e312e3d.394.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d93f9a0e97f3dadbb18f5e9ee3ae1b2a6c8546c057e62bfbf708394272ea490
3
+ size 4184
runs/Apr16_19-14-36_7a868e312e3d/events.out.tfevents.1713295090.7a868e312e3d.702.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf40df35ffd6a71d54ae5ebf45f14a72e0e4be8871a40637d97e721f2ea9430d
3
+ size 4184
runs/Apr16_19-39-25_ccd0e5f89ee3/events.out.tfevents.1713296786.ccd0e5f89ee3.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e4c74ff366b7d34489a98feb9b6f0ee25b2cdc300fdc92aeb187fc7497ca415
3
+ size 10547
runs/Apr16_20-10-45_ccd0e5f89ee3/events.out.tfevents.1713298247.ccd0e5f89ee3.385.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b1bbd75f08065ea5fad8cf64174c4145cfae5d43db906d390491c109ad7214
3
+ size 4184
runs/Apr16_21-42-23_ba1b200fa8ac/events.out.tfevents.1713304105.ba1b200fa8ac.82.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94317292928408cc1426db44cc6c5bd41b06a9049f65a06fc757059f7178ce15
3
+ size 6451
runs/Apr16_22-34-57_5439874391db/events.out.tfevents.1713306905.5439874391db.86.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8459016aef7e1d68f8eaadf6740630368b4962192a6adbe791abfd2a60d1c2d
3
+ size 6659
runs/Apr16_22-39-06_5439874391db/events.out.tfevents.1713307152.5439874391db.86.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a36c80248f9490c2cd8a79184766ee5a29bc5d7a4a974515843a7b36aa839a7
3
+ size 52683
runs/Apr16_22-39-06_5439874391db/events.out.tfevents.1713330526.5439874391db.86.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3738411f49823ad862dde1bb8f83fe8ef49012117889277691ec942b4d608d9a
3
+ size 411
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6602863174aec8eb964caea8c7925627ffd55918d0a6fc55e1875fd99b6b4c
3
+ size 4984