Hugging Face's logo

FerhatDk
/
wav2vec2-base-finetuned-ks

Audio Classification
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
FerhatDk commited on
Commit
c91d261
·
1 Parent(s): 7f8022a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -31
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6810
20
- - Accuracy: 0.6471
21
 
22
  ## Model description
23
 
@@ -50,36 +50,36 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | No log | 1.0 | 5 | 0.6810 | 0.6471 |
54
- | 0.6835 | 2.0 | 10 | 0.6785 | 0.6471 |
55
- | 0.6835 | 3.0 | 15 | 0.6748 | 0.6471 |
56
- | 0.6745 | 4.0 | 20 | 0.6715 | 0.6471 |
57
- | 0.6745 | 5.0 | 25 | 0.6688 | 0.6471 |
58
- | 0.6773 | 6.0 | 30 | 0.6622 | 0.6471 |
59
- | 0.6773 | 7.0 | 35 | 0.6585 | 0.6471 |
60
- | 0.6663 | 8.0 | 40 | 0.6553 | 0.6471 |
61
- | 0.6663 | 9.0 | 45 | 0.6539 | 0.6471 |
62
- | 0.6254 | 10.0 | 50 | 0.6514 | 0.6471 |
63
- | 0.6254 | 11.0 | 55 | 0.6506 | 0.6471 |
64
- | 0.6697 | 12.0 | 60 | 0.6498 | 0.6471 |
65
- | 0.6697 | 13.0 | 65 | 0.6604 | 0.6471 |
66
- | 0.6485 | 14.0 | 70 | 0.6556 | 0.6471 |
67
- | 0.6485 | 15.0 | 75 | 0.6504 | 0.6471 |
68
- | 0.6802 | 16.0 | 80 | 0.6636 | 0.6471 |
69
- | 0.6802 | 17.0 | 85 | 0.6521 | 0.6471 |
70
- | 0.6737 | 18.0 | 90 | 0.6494 | 0.6471 |
71
- | 0.6737 | 19.0 | 95 | 0.6494 | 0.6471 |
72
- | 0.6687 | 20.0 | 100 | 0.6493 | 0.6471 |
73
- | 0.6687 | 21.0 | 105 | 0.6500 | 0.6471 |
74
- | 0.6456 | 22.0 | 110 | 0.6500 | 0.6471 |
75
- | 0.6456 | 23.0 | 115 | 0.6493 | 0.6471 |
76
- | 0.6448 | 24.0 | 120 | 0.6493 | 0.6471 |
77
- | 0.6448 | 25.0 | 125 | 0.6495 | 0.6471 |
78
 
79
 
80
  ### Framework versions
81
 
82
- - Transformers 4.26.1
83
- - Pytorch 1.13.1+cu116
84
- - Datasets 2.9.0
85
- - Tokenizers 0.13.2
 
16
 
17
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5131
20
+ - Accuracy: 0.8545
21
 
22
  ## Model description
23
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 8 | 0.6930 | 0.4182 |
54
+ | 0.6924 | 2.0 | 16 | 0.6835 | 0.6 |
55
+ | 0.6802 | 3.0 | 24 | 0.6618 | 0.6909 |
56
+ | 0.649 | 4.0 | 32 | 0.6318 | 0.6364 |
57
+ | 0.6306 | 5.0 | 40 | 0.6066 | 0.6545 |
58
+ | 0.6306 | 6.0 | 48 | 0.5750 | 0.6545 |
59
+ | 0.597 | 7.0 | 56 | 0.5462 | 0.6909 |
60
+ | 0.5569 | 8.0 | 64 | 0.5165 | 0.7455 |
61
+ | 0.5379 | 9.0 | 72 | 0.4870 | 0.7818 |
62
+ | 0.4663 | 10.0 | 80 | 0.4436 | 0.8727 |
63
+ | 0.4663 | 11.0 | 88 | 0.4749 | 0.8364 |
64
+ | 0.4581 | 12.0 | 96 | 0.3678 | 0.8909 |
65
+ | 0.4244 | 13.0 | 104 | 0.4135 | 0.8545 |
66
+ | 0.3686 | 14.0 | 112 | 0.3410 | 0.9455 |
67
+ | 0.308 | 15.0 | 120 | 0.3530 | 0.8909 |
68
+ | 0.308 | 16.0 | 128 | 0.4086 | 0.8364 |
69
+ | 0.2677 | 17.0 | 136 | 0.3900 | 0.8545 |
70
+ | 0.2419 | 18.0 | 144 | 0.2027 | 0.9455 |
71
+ | 0.1973 | 19.0 | 152 | 0.3836 | 0.8727 |
72
+ | 0.1483 | 20.0 | 160 | 0.3371 | 0.8909 |
73
+ | 0.1483 | 21.0 | 168 | 0.5328 | 0.8 |
74
+ | 0.2048 | 22.0 | 176 | 0.3533 | 0.8909 |
75
+ | 0.2232 | 23.0 | 184 | 0.4151 | 0.8727 |
76
+ | 0.1864 | 24.0 | 192 | 0.2016 | 0.9273 |
77
+ | 0.2669 | 25.0 | 200 | 0.5131 | 0.8545 |
78
 
79
 
80
  ### Framework versions
81
 
82
+ - Transformers 4.29.2
83
+ - Pytorch 2.0.1+cu118
84
+ - Datasets 2.12.0
85
+ - Tokenizers 0.13.3