Hugging Face's logo

nacielo
/
hubert2BertMusic200

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
speech-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nacielo commited on
Commit
30d440b
•
1 Parent(s): 929d5ae

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -18
README.md CHANGED
@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.4375
20
- - Rouge1: 29.0195
21
- - Rouge2: 7.3975
22
- - Rougel: 20.4993
23
- - Rougelsum: 20.3634
24
- - Gen Len: 52.81
25
 
26
  ## Model description
27
 
@@ -40,28 +40,38 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 1e-05
44
  - train_batch_size: 4
45
  - eval_batch_size: 4
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 10
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
54
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
55
- | 1.8641 | 1.0 | 1361 | 1.6566 | 29.2626 | 7.4871 | 20.625 | 20.5664 | 60.57 |
56
- | 1.7169 | 2.0 | 2722 | 1.5973 | 26.9521 | 7.8677 | 19.7208 | 19.6278 | 50.38 |
57
- | 1.6726 | 3.0 | 4083 | 1.5585 | 30.2177 | 7.3497 | 20.92 | 20.8207 | 60.63 |
58
- | 1.628 | 4.0 | 5444 | 1.5186 | 28.2694 | 7.5824 | 19.796 | 19.7173 | 56.45 |
59
- | 1.6528 | 5.0 | 6805 | 1.4964 | 27.9623 | 7.8577 | 20.0053 | 19.92 | 52.75 |
60
- | 1.6151 | 6.0 | 8166 | 1.4718 | 30.3355 | 7.9194 | 20.9989 | 20.9562 | 55.94 |
61
- | 1.6218 | 7.0 | 9527 | 1.4591 | 27.9266 | 7.673 | 20.1116 | 20.0565 | 54.25 |
62
- | 1.6252 | 8.0 | 10888 | 1.4481 | 28.8105 | 7.6804 | 20.5785 | 20.4439 | 52.84 |
63
- | 1.6551 | 9.0 | 12249 | 1.4407 | 28.4905 | 7.2818 | 20.0679 | 19.9556 | 55.59 |
64
- | 1.6986 | 10.0 | 13610 | 1.4375 | 29.0195 | 7.3975 | 20.4993 | 20.3634 | 52.81 |
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.4016
20
+ - Rouge1: 29.7694
21
+ - Rouge2: 6.8881
22
+ - Rougel: 20.8382
23
+ - Rougelsum: 20.7475
24
+ - Gen Len: 54.68
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 1e-06
44
  - train_batch_size: 4
45
  - eval_batch_size: 4
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 20
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
54
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
55
+ | 1.5312 | 1.0 | 1361 | 1.4350 | 29.7078 | 7.6167 | 21.0154 | 20.9599 | 57.96 |
56
+ | 1.479 | 2.0 | 2722 | 1.4311 | 29.5523 | 7.5127 | 20.8746 | 20.7455 | 55.77 |
57
+ | 1.4774 | 3.0 | 4083 | 1.4296 | 29.4948 | 7.41 | 20.6514 | 20.531 | 55.12 |
58
+ | 1.4663 | 4.0 | 5444 | 1.4239 | 28.8275 | 6.8898 | 20.1906 | 20.1528 | 54.0 |
59
+ | 1.5195 | 5.0 | 6805 | 1.4219 | 31.4265 | 7.8481 | 21.8264 | 21.7471 | 53.33 |
60
+ | 1.5115 | 6.0 | 8166 | 1.4177 | 29.8254 | 6.8757 | 21.0269 | 20.9813 | 53.45 |
61
+ | 1.5424 | 7.0 | 9527 | 1.4154 | 29.9847 | 7.0621 | 20.9479 | 20.9081 | 54.73 |
62
+ | 1.5635 | 8.0 | 10888 | 1.4131 | 29.8807 | 7.1097 | 20.9508 | 20.902 | 53.83 |
63
+ | 1.6138 | 9.0 | 12249 | 1.4113 | 29.1418 | 6.725 | 20.4919 | 20.404 | 55.46 |
64
+ | 1.676 | 10.0 | 13610 | 1.4094 | 29.4633 | 6.7466 | 20.5997 | 20.5457 | 54.8 |
65
+ | 1.6447 | 11.0 | 14971 | 1.4087 | 30.1765 | 6.7892 | 20.9128 | 20.8485 | 54.75 |
66
+ | 1.6683 | 12.0 | 16332 | 1.4074 | 29.7832 | 6.7904 | 20.6381 | 20.5824 | 54.86 |
67
+ | 1.6927 | 13.0 | 17693 | 1.4056 | 29.5094 | 6.6848 | 20.5682 | 20.4713 | 53.62 |
68
+ | 1.6567 | 14.0 | 19054 | 1.4040 | 29.674 | 6.7272 | 20.7709 | 20.7017 | 52.78 |
69
+ | 1.672 | 15.0 | 20415 | 1.4032 | 29.447 | 6.6842 | 20.707 | 20.6147 | 53.81 |
70
+ | 1.6468 | 16.0 | 21776 | 1.4032 | 30.1311 | 7.1838 | 21.0813 | 21.0099 | 54.62 |
71
+ | 1.6661 | 17.0 | 23137 | 1.4022 | 30.1715 | 7.1566 | 21.0716 | 20.9984 | 54.95 |
72
+ | 1.668 | 18.0 | 24498 | 1.4020 | 30.1766 | 7.1429 | 21.1461 | 21.0611 | 54.56 |
73
+ | 1.6448 | 19.0 | 25859 | 1.4016 | 29.5354 | 6.7505 | 20.5517 | 20.4719 | 54.34 |
74
+ | 1.6647 | 20.0 | 27220 | 1.4016 | 29.7694 | 6.8881 | 20.8382 | 20.7475 | 54.68 |
75
 
76
 
77
  ### Framework versions