aryamtos commited on
Commit
331f56f
1 Parent(s): 8fb7497

End of training

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 36.36363636363637
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.7668
36
- - Wer Ortho: 35.9655
37
- - Wer: 36.3636
38
 
39
  ## Model description
40
 
@@ -53,7 +53,7 @@ More information needed
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
- - learning_rate: 3e-05
57
  - train_batch_size: 16
58
  - eval_batch_size: 16
59
  - seed: 42
@@ -66,14 +66,14 @@ The following hyperparameters were used during training:
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
70
- |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
71
- | 0.0001 | 428.57 | 500 | 0.7668 | 35.9655 | 36.3636 |
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.33.3
77
  - Pytorch 2.1.0+cu118
78
- - Datasets 2.14.6.dev0
79
  - Tokenizers 0.13.3
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.3600944510035419
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.8044
36
+ - Wer Ortho: 0.3560
37
+ - Wer: 0.3601
38
 
39
  ## Model description
40
 
 
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
+ - learning_rate: 5e-05
57
  - train_batch_size: 16
58
  - eval_batch_size: 16
59
  - seed: 42
 
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
70
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|
71
+ | 0.0 | 428.57 | 500 | 0.8044 | 0.3560 | 0.3601 |
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.33.3
77
  - Pytorch 2.1.0+cu118
78
+ - Datasets 2.14.7.dev0
79
  - Tokenizers 0.13.3