abbenedek commited on
Commit
1bf5109
1 Parent(s): bfbb6d3

End of training

Browse files
Files changed (2) hide show
  1. README.md +38 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,8 +1,10 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: openai/whisper-tiny.en
 
6
  model-index:
7
  - name: whisper-tiny.en-finetuned
8
  results: []
@@ -15,13 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 1.3394
19
- - eval_wer: 0.5
20
- - eval_runtime: 51.3485
21
- - eval_samples_per_second: 3.895
22
- - eval_steps_per_second: 0.136
23
- - epoch: 3.8
24
- - step: 190
25
 
26
  ## Model description
27
 
@@ -41,15 +40,43 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 1e-06
44
- - train_batch_size: 16
45
- - eval_batch_size: 32
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 20
50
- - training_steps: 1000
51
  - mixed_precision_training: Native AMP
52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  ### Framework versions
54
 
55
  - Transformers 4.39.3
 
1
  ---
2
  license: apache-2.0
3
+ base_model: openai/whisper-tiny.en
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: whisper-tiny.en-finetuned
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.4890
21
+ - Wer: 0.8750
22
+ - Cer: 0.4454
23
+ - Ser: 0.055
 
 
 
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 1e-06
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 64
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 20
49
+ - training_steps: 220
50
  - mixed_precision_training: Native AMP
51
 
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Ser |
55
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:-----:|
56
+ | 6.4419 | 0.4 | 10 | 6.4480 | 45.25 | 16.3573 | 1.0 |
57
+ | 6.2706 | 0.8 | 20 | 5.9268 | 39.375 | 14.1797 | 1.0 |
58
+ | 5.3444 | 1.2 | 30 | 4.8418 | 19.875 | 7.3002 | 1.0 |
59
+ | 4.3269 | 1.6 | 40 | 3.9103 | 9.375 | 3.8357 | 1.0 |
60
+ | 3.6103 | 2.0 | 50 | 3.3228 | 7.0000 | 3.2170 | 1.0 |
61
+ | 3.0331 | 2.4 | 60 | 2.7725 | 5.375 | 2.3509 | 1.0 |
62
+ | 2.5529 | 2.8 | 70 | 2.3913 | 4.75 | 1.8312 | 1.0 |
63
+ | 2.2359 | 3.2 | 80 | 2.1217 | 3.375 | 1.4353 | 1.0 |
64
+ | 1.9777 | 3.6 | 90 | 1.8790 | 3.0 | 1.3116 | 1.0 |
65
+ | 1.7863 | 4.0 | 100 | 1.7402 | 2.875 | 1.0393 | 0.98 |
66
+ | 1.6854 | 4.4 | 110 | 1.6736 | 2.625 | 0.9651 | 0.925 |
67
+ | 1.6297 | 4.8 | 120 | 1.6290 | 2.625 | 0.9404 | 0.765 |
68
+ | 1.5974 | 5.2 | 130 | 1.5959 | 2.5 | 0.9651 | 0.57 |
69
+ | 1.5673 | 5.6 | 140 | 1.5702 | 1.5 | 0.6434 | 0.385 |
70
+ | 1.5397 | 6.0 | 150 | 1.5497 | 1.25 | 0.5692 | 0.27 |
71
+ | 1.524 | 6.4 | 160 | 1.5333 | 1.125 | 0.5444 | 0.22 |
72
+ | 1.509 | 6.8 | 170 | 1.5199 | 0.8750 | 0.4454 | 0.155 |
73
+ | 1.4986 | 7.2 | 180 | 1.5091 | 0.8750 | 0.4454 | 0.095 |
74
+ | 1.4872 | 7.6 | 190 | 1.5011 | 0.8750 | 0.4454 | 0.075 |
75
+ | 1.4844 | 8.0 | 200 | 1.4950 | 0.8750 | 0.4454 | 0.075 |
76
+ | 1.4743 | 8.4 | 210 | 1.4910 | 0.8750 | 0.4454 | 0.065 |
77
+ | 1.4746 | 8.8 | 220 | 1.4890 | 0.8750 | 0.4454 | 0.055 |
78
+
79
+
80
  ### Framework versions
81
 
82
  - Transformers 4.39.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764a2d42f5b996b875d684478f5769b467264b148941d3f4a127bbd90d3e6d8a
3
  size 151060136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98015194c391d4fb44fd532131e9d0c40382a97c5fbdcad2fc4bf16824e3ff2d
3
  size 151060136