Hugging Face's logo

202015004
/
Spoof_detection

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
202015004 commited on
Commit
a80f9a3
·
1 Parent(s): 558c355

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: Spoof_detection
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # Spoof_detection
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.7526
18
+ - Wer: 0.1090
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 30
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
+ | 82.2809 | 0.66 | 500 | 4.5229 | 0.1090 |
52
+ | 1.8956 | 1.33 | 1000 | 1.8185 | 0.1090 |
53
+ | 1.842 | 1.99 | 1500 | 1.9392 | 0.1090 |
54
+ | 1.8254 | 2.65 | 2000 | 2.0335 | 0.1090 |
55
+ | 1.8168 | 3.32 | 2500 | 1.8399 | 0.1090 |
56
+ | 1.8353 | 3.98 | 3000 | 1.7997 | 0.1090 |
57
+ | 1.8287 | 4.64 | 3500 | 1.7079 | 0.1090 |
58
+ | 1.8191 | 5.31 | 4000 | 1.7340 | 0.1090 |
59
+ | 1.8111 | 5.97 | 4500 | 1.6820 | 0.1090 |
60
+ | 1.7992 | 6.63 | 5000 | 1.7079 | 0.1090 |
61
+ | 1.7967 | 7.29 | 5500 | 1.7308 | 0.1090 |
62
+ | 1.784 | 7.96 | 6000 | 1.7111 | 0.1090 |
63
+ | 1.7859 | 8.62 | 6500 | 1.7576 | 0.1090 |
64
+ | 1.7828 | 9.28 | 7000 | 1.8259 | 0.1090 |
65
+ | 1.7894 | 9.95 | 7500 | 1.7357 | 0.1090 |
66
+ | 1.7771 | 10.61 | 8000 | 1.9608 | 0.1090 |
67
+ | 1.7682 | 11.27 | 8500 | 1.9535 | 0.1090 |
68
+ | 1.7665 | 11.94 | 9000 | 1.9277 | 0.1090 |
69
+ | 1.7672 | 12.6 | 9500 | 1.8406 | 0.1090 |
70
+ | 1.7577 | 13.26 | 10000 | 1.7859 | 0.1090 |
71
+ | 1.7617 | 13.93 | 10500 | 1.8030 | 0.1090 |
72
+ | 1.7625 | 14.59 | 11000 | 1.7567 | 0.1090 |
73
+ | 1.7586 | 15.25 | 11500 | 1.7667 | 0.1090 |
74
+ | 1.7526 | 15.92 | 12000 | 1.7477 | 0.1090 |
75
+ | 1.7533 | 16.58 | 12500 | 1.7285 | 0.1090 |
76
+ | 1.75 | 17.24 | 13000 | 1.7542 | 0.1090 |
77
+ | 1.7491 | 17.9 | 13500 | 1.7653 | 0.1090 |
78
+ | 1.7483 | 18.57 | 14000 | 1.7344 | 0.1090 |
79
+ | 1.7476 | 19.23 | 14500 | 1.7156 | 0.1090 |
80
+ | 1.745 | 19.89 | 15000 | 1.7431 | 0.1090 |
81
+ | 1.7422 | 20.56 | 15500 | 1.7591 | 0.1090 |
82
+ | 1.744 | 21.22 | 16000 | 1.7794 | 0.1090 |
83
+ | 1.743 | 21.88 | 16500 | 1.6921 | 0.1090 |
84
+ | 1.7385 | 22.55 | 17000 | 1.7567 | 0.1090 |
85
+ | 1.7405 | 23.21 | 17500 | 1.7527 | 0.1090 |
86
+ | 1.7392 | 23.87 | 18000 | 1.7879 | 0.1090 |
87
+ | 1.7388 | 24.54 | 18500 | 1.8047 | 0.1090 |
88
+ | 1.7338 | 25.2 | 19000 | 1.7589 | 0.1090 |
89
+ | 1.7368 | 25.86 | 19500 | 1.7774 | 0.1090 |
90
+ | 1.7347 | 26.53 | 20000 | 1.7601 | 0.1090 |
91
+ | 1.7349 | 27.19 | 20500 | 1.7783 | 0.1090 |
92
+ | 1.7329 | 27.85 | 21000 | 1.7327 | 0.1090 |
93
+ | 1.7306 | 28.51 | 21500 | 1.7403 | 0.1090 |
94
+ | 1.7339 | 29.18 | 22000 | 1.7594 | 0.1090 |
95
+ | 1.7304 | 29.84 | 22500 | 1.7526 | 0.1090 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.17.0
101
+ - Pytorch 1.10.0+cu102
102
+ - Datasets 1.16.1
103
+ - Tokenizers 0.12.1