zakria commited on
Commit
6750d09
·
1 Parent(s): 2561817

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +87 -0
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: Project_NLP
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
+ # Project_NLP
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.5324
18
+ - Wer: 0.3355
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: 8
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
+ | 3.5697 | 1.0 | 500 | 2.1035 | 0.9979 |
52
+ | 0.8932 | 2.01 | 1000 | 0.5649 | 0.5621 |
53
+ | 0.4363 | 3.01 | 1500 | 0.4326 | 0.4612 |
54
+ | 0.3035 | 4.02 | 2000 | 0.4120 | 0.4191 |
55
+ | 0.2343 | 5.02 | 2500 | 0.4199 | 0.3985 |
56
+ | 0.1921 | 6.02 | 3000 | 0.4380 | 0.4043 |
57
+ | 0.1549 | 7.03 | 3500 | 0.4456 | 0.3925 |
58
+ | 0.1385 | 8.03 | 4000 | 0.4264 | 0.3871 |
59
+ | 0.1217 | 9.04 | 4500 | 0.4744 | 0.3774 |
60
+ | 0.1041 | 10.04 | 5000 | 0.4498 | 0.3745 |
61
+ | 0.0968 | 11.04 | 5500 | 0.4716 | 0.3628 |
62
+ | 0.0893 | 12.05 | 6000 | 0.4680 | 0.3764 |
63
+ | 0.078 | 13.05 | 6500 | 0.5100 | 0.3623 |
64
+ | 0.0704 | 14.06 | 7000 | 0.4893 | 0.3552 |
65
+ | 0.0659 | 15.06 | 7500 | 0.4956 | 0.3565 |
66
+ | 0.0578 | 16.06 | 8000 | 0.5450 | 0.3595 |
67
+ | 0.0563 | 17.07 | 8500 | 0.4891 | 0.3614 |
68
+ | 0.0557 | 18.07 | 9000 | 0.5307 | 0.3548 |
69
+ | 0.0447 | 19.08 | 9500 | 0.4923 | 0.3493 |
70
+ | 0.0456 | 20.08 | 10000 | 0.5156 | 0.3479 |
71
+ | 0.0407 | 21.08 | 10500 | 0.4979 | 0.3389 |
72
+ | 0.0354 | 22.09 | 11000 | 0.5549 | 0.3462 |
73
+ | 0.0322 | 23.09 | 11500 | 0.5601 | 0.3439 |
74
+ | 0.0342 | 24.1 | 12000 | 0.5131 | 0.3451 |
75
+ | 0.0276 | 25.1 | 12500 | 0.5206 | 0.3392 |
76
+ | 0.0245 | 26.1 | 13000 | 0.5337 | 0.3373 |
77
+ | 0.0226 | 27.11 | 13500 | 0.5311 | 0.3353 |
78
+ | 0.0229 | 28.11 | 14000 | 0.5375 | 0.3373 |
79
+ | 0.0225 | 29.12 | 14500 | 0.5324 | 0.3355 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.17.0
85
+ - Pytorch 1.11.0+cu113
86
+ - Datasets 1.18.3
87
+ - Tokenizers 0.12.1