Hugging Face's logo

gokuls
/
whisper-base.en-fsc

TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files Metrics Community
gokuls commited on
Commit
fc3d021
•
1 Parent(s): 6da53c8

End of training

Browse files
Files changed (3) hide show
  1. README.md +29 -24
  2. model.safetensors +1 -1
  3. runs/Oct04_09-00-00_ki-g0010/events.out.tfevents.1728078045.ki-g0010.2032512.1 +3 -0
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 3.0278
21
- - Accuracy: 0.5630
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 5e-05
41
  - train_batch_size: 48
42
  - eval_batch_size: 48
43
  - seed: 42
@@ -46,32 +46,37 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - num_epochs: 20
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
55
- | No log | 0.9972 | 263 | 3.7447 | 0.0962 |
56
- | No log | 1.9981 | 527 | 2.8087 | 0.3060 |
57
- | No log | 2.9991 | 791 | 2.3083 | 0.4062 |
58
- | 2.9232 | 4.0 | 1055 | 2.0094 | 0.4940 |
59
- | 2.9232 | 4.9972 | 1318 | 1.9099 | 0.5321 |
60
- | 2.9232 | 5.9981 | 1582 | 1.9257 | 0.5479 |
61
- | 2.9232 | 6.9991 | 1846 | 2.0132 | 0.5479 |
62
- | 0.8199 | 8.0 | 2110 | 2.1486 | 0.5444 |
63
- | 0.8199 | 8.9972 | 2373 | 2.2976 | 0.5440 |
64
- | 0.8199 | 9.9981 | 2637 | 2.4131 | 0.5453 |
65
- | 0.8199 | 10.9991 | 2901 | 2.5031 | 0.5523 |
66
- | 0.1503 | 12.0 | 3165 | 2.6273 | 0.5544 |
67
- | 0.1503 | 12.9972 | 3428 | 2.7233 | 0.5581 |
68
- | 0.1503 | 13.9981 | 3692 | 2.8470 | 0.5498 |
69
- | 0.1503 | 14.9991 | 3956 | 2.8848 | 0.5589 |
70
- | 0.0246 | 16.0 | 4220 | 2.9497 | 0.5605 |
71
- | 0.0246 | 16.9972 | 4483 | 2.9992 | 0.5612 |
72
- | 0.0246 | 17.9981 | 4747 | 3.0278 | 0.5630 |
73
- | 0.0043 | 18.9991 | 5011 | 3.0502 | 0.5629 |
74
- | 0.0043 | 19.9431 | 5260 | 3.0561 | 0.5629 |
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0437
21
+ - Accuracy: 0.9950
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 0.0005
41
  - train_batch_size: 48
42
  - eval_batch_size: 48
43
  - seed: 42
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 25
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
55
+ | No log | 0.9959 | 120 | 0.0862 | 0.9739 |
56
+ | No log | 2.0 | 241 | 0.0422 | 0.9866 |
57
+ | No log | 2.9959 | 361 | 0.0630 | 0.9823 |
58
+ | No log | 4.0 | 482 | 0.0630 | 0.9805 |
59
+ | No log | 4.9959 | 602 | 0.0626 | 0.9821 |
60
+ | No log | 6.0 | 723 | 0.0339 | 0.9905 |
61
+ | No log | 6.9959 | 843 | 0.0452 | 0.9897 |
62
+ | No log | 8.0 | 964 | 0.0527 | 0.9834 |
63
+ | 0.1514 | 8.9959 | 1084 | 0.0637 | 0.9868 |
64
+ | 0.1514 | 10.0 | 1205 | 0.0443 | 0.9921 |
65
+ | 0.1514 | 10.9959 | 1325 | 0.0306 | 0.9937 |
66
+ | 0.1514 | 12.0 | 1446 | 0.0416 | 0.9897 |
67
+ | 0.1514 | 12.9959 | 1566 | 0.0363 | 0.9910 |
68
+ | 0.1514 | 14.0 | 1687 | 0.0413 | 0.9924 |
69
+ | 0.1514 | 14.9959 | 1807 | 0.0344 | 0.9945 |
70
+ | 0.1514 | 16.0 | 1928 | 0.0508 | 0.9924 |
71
+ | 0.0161 | 16.9959 | 2048 | 0.0436 | 0.9937 |
72
+ | 0.0161 | 18.0 | 2169 | 0.0435 | 0.9931 |
73
+ | 0.0161 | 18.9959 | 2289 | 0.0428 | 0.9945 |
74
+ | 0.0161 | 20.0 | 2410 | 0.0425 | 0.9947 |
75
+ | 0.0161 | 20.9959 | 2530 | 0.0432 | 0.9947 |
76
+ | 0.0161 | 22.0 | 2651 | 0.0438 | 0.9947 |
77
+ | 0.0161 | 22.9959 | 2771 | 0.0437 | 0.9950 |
78
+ | 0.0161 | 24.0 | 2892 | 0.0438 | 0.9950 |
79
+ | 0.0011 | 24.8963 | 3000 | 0.0438 | 0.9950 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fe27d93e73d0db767648e1c46d8c5ad9dc20b755092b447c942814108302f02
3
  size 82904384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55c8c6f4617b884171a71b5ca7b1330325e6516e1257a7c57ec28bd271d5e79
3
  size 82904384
runs/Oct04_09-00-00_ki-g0010/events.out.tfevents.1728078045.ki-g0010.2032512.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7b243a07683f696dcca41f4115d37f0645024c610e33f3f7602300cb9be9c4
3
+ size 411