Hugging Face's logo

nocturneFlow
/
whisper-small-fleurs-augmented-kk

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Kazakh
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
nocturneFlow commited on
Commit
830bf2e
·
verified ·
1 Parent(s): 49a8a31

End of training

Browse files
Files changed (3) hide show
  1. README.md +8 -8
  2. model.safetensors +1 -1
  3. runs/Feb23_21-16-49_DESKTOP-VBR63RT/events.out.tfevents.1740327414.DESKTOP-VBR63RT.29804.0 +2 -2
README.md CHANGED
@@ -25,7 +25,7 @@ model-index:
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 27.064871812216733
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
35
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Fleurs dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.2581
39
- - Wer: 27.0649
40
 
41
  ## Model description
42
 
@@ -69,11 +69,11 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
72
- | 0.8313 | 1.0 | 200 | 0.3977 | 44.0371 |
73
- | 0.489 | 2.0 | 400 | 0.2842 | 31.9894 |
74
- | 0.2973 | 3.0 | 600 | 0.2600 | 28.1404 |
75
- | 0.2323 | 4.0 | 800 | 0.2551 | 27.0919 |
76
- | 0.1469 | 5.0 | 1000 | 0.2581 | 27.0649 |
77
 
78
 
79
  ### Framework versions
 
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 22.28911587634445
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
35
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Fleurs dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.2814
39
+ - Wer: 22.2891
40
 
41
  ## Model description
42
 
 
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
72
+ | 0.3714 | 1.0 | 200 | 0.2556 | 23.7164 |
73
+ | 0.2797 | 2.0 | 400 | 0.2565 | 23.1212 |
74
+ | 0.1609 | 3.0 | 600 | 0.2644 | 22.2688 |
75
+ | 0.084 | 4.0 | 800 | 0.2738 | 22.3906 |
76
+ | 0.059 | 5.0 | 1000 | 0.2814 | 22.2891 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d6ff029f87f84261c1fb7378b930fee931a05ebe091e885855092d87362b7c1
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ddaa37f5bb140127e1a9e5575e6bfca63eacc02a8bb4fbf302a8f7a0d8a923
3
  size 966995080
runs/Feb23_21-16-49_DESKTOP-VBR63RT/events.out.tfevents.1740327414.DESKTOP-VBR63RT.29804.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c82543ab1c8f0ac132056996c084930b037507de082a3f3fdba34b688706902a
3
- size 16007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc0b55d0cfee82972a7cc21ae89805239a358afcaa3f94d5ab29f7a356b1d065
3
+ size 16361