Hugging Face's logo

cogniveon
/
wav2vec2-base-960h

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
cogniveon commited on
Commit
9fbc263
•
1 Parent(s): 53390a2

initial commit

Browse files
Files changed (7) hide show
  1. README.md +82 -0
  2. config.json +120 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/May03_14-19-09_4a22c8285708/events.out.tfevents.1714745960.4a22c8285708.4986.3 +3 -0
  6. runs/May03_21-19-56_4a22c8285708/events.out.tfevents.1714771254.4a22c8285708.4986.4 +3 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base-960h
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: wav2vec2-base-960h
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # wav2vec2-base-960h
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Accuracy: 0.8830
21
+ - Loss: 0.4259
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 3e-05
41
+ - train_batch_size: 5
42
+ - eval_batch_size: 5
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 20
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 20
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
55
+ | 0.7016 | 1.0 | 125 | 0.7933 | 0.6439 |
56
+ | 0.7121 | 2.0 | 250 | 0.5962 | 0.7870 |
57
+ | 0.4491 | 3.0 | 375 | 0.8782 | 0.4561 |
58
+ | 0.4606 | 4.0 | 500 | 0.8526 | 0.5664 |
59
+ | 0.425 | 5.0 | 625 | 0.8718 | 0.4652 |
60
+ | 0.4852 | 6.0 | 750 | 0.8397 | 0.5111 |
61
+ | 0.3023 | 7.0 | 875 | 0.8766 | 0.4319 |
62
+ | 0.2247 | 8.0 | 1000 | 0.8654 | 0.5093 |
63
+ | 0.4269 | 9.0 | 1125 | 0.8926 | 0.4148 |
64
+ | 0.348 | 10.0 | 1250 | 0.8846 | 0.3861 |
65
+ | 0.5049 | 11.0 | 1375 | 0.8814 | 0.4141 |
66
+ | 0.2305 | 12.0 | 1500 | 0.8878 | 0.3804 |
67
+ | 0.2839 | 13.0 | 1625 | 0.8990 | 0.3682 |
68
+ | 0.1739 | 14.0 | 1750 | 0.9022 | 0.3917 |
69
+ | 0.2808 | 15.0 | 1875 | 0.8926 | 0.4303 |
70
+ | 0.2306 | 16.0 | 2000 | 0.9006 | 0.3951 |
71
+ | 0.2766 | 17.0 | 2125 | 0.8974 | 0.4003 |
72
+ | 0.1212 | 18.0 | 2250 | 0.8910 | 0.3999 |
73
+ | 0.2822 | 19.0 | 2375 | 0.8766 | 0.4390 |
74
+ | 0.1391 | 20.0 | 2500 | 0.8830 | 0.4259 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.40.1
80
+ - Pytorch 2.2.1+cu121
81
+ - Datasets 2.19.0
82
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
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": "Absent",
63
+ "1": "Present",
64
+ "2": "Unknown"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 3072,
68
+ "label2id": {
69
+ "Absent": "0",
70
+ "Present": "1",
71
+ "Unknown": "2"
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "layerdrop": 0.1,
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_prob": 0.05,
81
+ "model_type": "wav2vec2",
82
+ "num_adapter_layers": 3,
83
+ "num_attention_heads": 12,
84
+ "num_codevector_groups": 2,
85
+ "num_codevectors_per_group": 320,
86
+ "num_conv_pos_embedding_groups": 16,
87
+ "num_conv_pos_embeddings": 128,
88
+ "num_feat_extract_layers": 7,
89
+ "num_hidden_layers": 12,
90
+ "num_negatives": 100,
91
+ "output_hidden_size": 768,
92
+ "pad_token_id": 0,
93
+ "proj_codevector_dim": 256,
94
+ "tdnn_dilation": [
95
+ 1,
96
+ 2,
97
+ 3,
98
+ 1,
99
+ 1
100
+ ],
101
+ "tdnn_dim": [
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 1500
107
+ ],
108
+ "tdnn_kernel": [
109
+ 5,
110
+ 3,
111
+ 3,
112
+ 1,
113
+ 1
114
+ ],
115
+ "torch_dtype": "float32",
116
+ "transformers_version": "4.40.1",
117
+ "use_weighted_layer_sum": false,
118
+ "vocab_size": 32,
119
+ "xvector_output_dim": 512
120
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55be8007cfc92a0f2af3ab4315a88dc38c8811d5a5693385ccf21e7354c25190
3
+ size 378303396
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/May03_14-19-09_4a22c8285708/events.out.tfevents.1714745960.4a22c8285708.4986.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28fa2b6d639cb769478d2f73fa882ef65f1280ef4c149ca341929d1f24cc44d7
3
+ size 118550
runs/May03_21-19-56_4a22c8285708/events.out.tfevents.1714771254.4a22c8285708.4986.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded71250a257afdc2752b739bee0a71da8a77daee6885f996acd93dfb5a2ed12
3
+ size 6696
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3183af2586e51a83782107467958c9e559e56d17539d6bc60dddfcfb680d8ed2
3
+ size 5048