marinone94 commited on
Commit
bb66eab
1 Parent(s): e4220c8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Wer
23
  type: wer
24
- value: 186.6677311192719
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the fleurs dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 1.0049
35
- - Wer: 186.6677
36
 
37
  ## Model description
38
 
@@ -65,21 +65,21 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 1.4112 | 0.1 | 44 | 1.4919 | 245.2978 |
69
- | 1.0501 | 0.2 | 88 | 1.2255 | 219.9425 |
70
- | 0.9033 | 0.29 | 132 | 1.1203 | 205.7800 |
71
- | 0.8142 | 1.06 | 176 | 1.0675 | 192.8788 |
72
- | 0.8029 | 1.16 | 220 | 1.0393 | 178.4289 |
73
- | 0.6324 | 1.25 | 264 | 1.0302 | 216.6055 |
74
- | 0.6971 | 2.02 | 308 | 1.0135 | 179.3709 |
75
- | 0.6051 | 2.12 | 352 | 1.0065 | 194.6352 |
76
- | 0.6048 | 2.21 | 396 | 1.0030 | 173.4792 |
77
- | 0.585 | 2.31 | 440 | 1.0049 | 186.6677 |
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.27.3
83
- - Pytorch 1.13.1+cu116
84
  - Datasets 2.10.1
85
- - Tokenizers 0.13.2
 
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 180.05748044068338
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the fleurs dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 1.0050
35
+ - Wer: 180.0575
36
 
37
  ## Model description
38
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.4112 | 0.1 | 44 | 1.4919 | 245.3457 |
69
+ | 1.0502 | 0.2 | 88 | 1.2255 | 220.1501 |
70
+ | 0.9033 | 0.29 | 132 | 1.1203 | 206.2430 |
71
+ | 0.8141 | 1.06 | 176 | 1.0675 | 201.9639 |
72
+ | 0.8029 | 1.16 | 220 | 1.0394 | 178.3650 |
73
+ | 0.6324 | 1.25 | 264 | 1.0301 | 221.2997 |
74
+ | 0.6972 | 2.02 | 308 | 1.0134 | 176.6725 |
75
+ | 0.6052 | 2.12 | 352 | 1.0065 | 194.7150 |
76
+ | 0.6047 | 2.21 | 396 | 1.0030 | 160.9133 |
77
+ | 0.5849 | 2.31 | 440 | 1.0050 | 180.0575 |
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.27.3
83
+ - Pytorch 2.0.0+cu118
84
  - Datasets 2.10.1
85
+ - Tokenizers 0.13.3