antonjaragon commited on
Commit
a3f69ef
1 Parent(s): f71dd20

Model save

Browse files
Files changed (2) hide show
  1. README.md +82 -0
  2. pytorch_model.bin +1 -1
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
+ - superb
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: wav2vec2-base-ft-keyword-spotting
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: superb
18
+ type: superb
19
+ config: ks
20
+ split: validation
21
+ args: ks
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9830832597822889
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-ft-keyword-spotting
32
+
33
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.0789
36
+ - Accuracy: 0.9831
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: 0
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: 5.0
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.4547 | 1.0 | 399 | 0.3372 | 0.9710 |
71
+ | 0.2625 | 2.0 | 798 | 0.1182 | 0.9779 |
72
+ | 0.1575 | 3.0 | 1197 | 0.0963 | 0.9787 |
73
+ | 0.1314 | 4.0 | 1597 | 0.0827 | 0.9832 |
74
+ | 0.1307 | 5.0 | 1995 | 0.0789 | 0.9831 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.32.0.dev0
80
+ - Pytorch 2.0.1+cu117
81
+ - Datasets 2.14.4
82
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83ddf327657ac208e97a6919c040a385ff44ead424b7920e70ec3b88dd7a4f34
3
  size 378360681
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef12682188b244fc57d939ac7d2062727c47badc420869c84d49a0e6202350a6
3
  size 378360681