Hugging Face's logo

vakanksha2002
/
whisper-tiny-en-US

TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
vakanksha2002 commited on
Commit
5afc26a
·
verified ·
1 Parent(s): ca9eb5c

End of training

Browse files
Files changed (2) hide show
  1. README.md +23 -31
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.3582458307597282
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: 1.0645
36
- - Wer Ortho: 0.3623
37
- - Wer: 0.3582
38
 
39
  ## Model description
40
 
@@ -53,40 +53,32 @@ More information needed
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
- - learning_rate: 1e-05
57
- - train_batch_size: 16
58
- - eval_batch_size: 16
59
  - seed: 42
 
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: constant_with_warmup
62
- - lr_scheduler_warmup_steps: 50
63
- - training_steps: 1000
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
69
- |:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|
70
- | 0.0003 | 1.7857 | 50 | 0.9458 | 0.3862 | 0.3792 |
71
- | 0.0018 | 3.5714 | 100 | 0.9438 | 0.3578 | 0.3490 |
72
- | 0.0021 | 5.3571 | 150 | 0.9330 | 0.3894 | 0.3811 |
73
- | 0.0008 | 7.1429 | 200 | 0.9398 | 0.3972 | 0.3928 |
74
- | 0.0003 | 8.9286 | 250 | 0.9701 | 0.3985 | 0.3953 |
75
- | 0.0006 | 10.7143 | 300 | 0.9799 | 0.3965 | 0.3928 |
76
- | 0.0002 | 12.5 | 350 | 0.9913 | 0.3669 | 0.3644 |
77
- | 0.0001 | 14.2857 | 400 | 0.9941 | 0.3540 | 0.3490 |
78
- | 0.0001 | 16.0714 | 450 | 1.0054 | 0.3585 | 0.3545 |
79
- | 0.0001 | 17.8571 | 500 | 1.0149 | 0.3585 | 0.3545 |
80
- | 0.0001 | 19.6429 | 550 | 1.0218 | 0.3527 | 0.3490 |
81
- | 0.0001 | 21.4286 | 600 | 1.0279 | 0.3598 | 0.3564 |
82
- | 0.0 | 23.2143 | 650 | 1.0336 | 0.3585 | 0.3552 |
83
- | 0.0 | 25.0 | 700 | 1.0389 | 0.3598 | 0.3564 |
84
- | 0.0 | 26.7857 | 750 | 1.0434 | 0.3611 | 0.3570 |
85
- | 0.0 | 28.5714 | 800 | 1.0486 | 0.3636 | 0.3595 |
86
- | 0.0 | 30.3571 | 850 | 1.0529 | 0.3636 | 0.3595 |
87
- | 0.0 | 32.1429 | 900 | 1.0571 | 0.3623 | 0.3582 |
88
- | 0.0 | 33.9286 | 950 | 1.0607 | 0.3623 | 0.3582 |
89
- | 0.0 | 35.7143 | 1000 | 1.0645 | 0.3623 | 0.3582 |
90
 
91
 
92
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.296010296010296
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: 0.4990
36
+ - Wer Ortho: 0.2965
37
+ - Wer: 0.2960
38
 
39
  ## Model description
40
 
 
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
+ - learning_rate: 5e-07
57
+ - train_batch_size: 2
58
+ - eval_batch_size: 2
59
  - seed: 42
60
+ - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 8
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: constant_with_warmup
64
+ - lr_scheduler_warmup_steps: 100
65
+ - training_steps: 500
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
71
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|
72
+ | 0.0244 | 0.8969 | 50 | 0.5282 | 0.3012 | 0.3005 |
73
+ | 0.0178 | 1.7937 | 100 | 0.5213 | 0.2985 | 0.2986 |
74
+ | 0.0171 | 2.6906 | 150 | 0.5147 | 0.2979 | 0.2967 |
75
+ | 0.0121 | 3.5874 | 200 | 0.5092 | 0.2925 | 0.2915 |
76
+ | 0.0071 | 4.4843 | 250 | 0.5057 | 0.3072 | 0.3069 |
77
+ | 0.0073 | 5.3812 | 300 | 0.5034 | 0.2945 | 0.2941 |
78
+ | 0.003 | 6.2780 | 350 | 0.5014 | 0.2945 | 0.2934 |
79
+ | 0.0036 | 7.1749 | 400 | 0.5003 | 0.2972 | 0.2967 |
80
+ | 0.0034 | 8.0717 | 450 | 0.4997 | 0.2965 | 0.2960 |
81
+ | 0.0034 | 8.9686 | 500 | 0.4990 | 0.2965 | 0.2960 |
 
 
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:add369d97ebd2006554789d0c1b9b57f9ac8f93f885d9f2b27187d2f57375403
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1838b20004b4d9fd06e6eb97118b6d1a316cadf2e6b18c6de0fa31bcc03d27e0
3
  size 151061672