Hugging Face's logo

ezrab
/
whisper-tiny-minds14

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ezrab commited on
Commit
1925b96
•
1 Parent(s): fd991dd

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -46
  2. model.safetensors +1 -1
  3. runs/Oct02_21-43-30_dfd2db00b841/events.out.tfevents.1727905411.dfd2db00b841.1583.1 +2 -2
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Wer
25
  type: wer
26
- value: 0.4964580873671783
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.9507
37
- - Wer Ortho: 0.4855
38
- - Wer: 0.4965
39
 
40
  ## Model description
41
 
@@ -54,60 +54,30 @@ More information needed
54
  ### Training hyperparameters
55
 
56
  The following hyperparameters were used during training:
57
- - learning_rate: 3e-05
58
  - train_batch_size: 16
59
  - eval_batch_size: 16
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: constant_with_warmup
63
  - lr_scheduler_warmup_steps: 50
64
- - training_steps: 2000
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
70
  |:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|
71
- | 0.7253 | 1.7857 | 50 | 0.5916 | 0.3751 | 0.3583 |
72
- | 0.158 | 3.5714 | 100 | 0.6146 | 0.3399 | 0.3235 |
73
- | 0.0244 | 5.3571 | 150 | 0.6676 | 0.3307 | 0.3264 |
74
- | 0.0127 | 7.1429 | 200 | 0.6988 | 0.3251 | 0.3188 |
75
- | 0.0065 | 8.9286 | 250 | 0.7239 | 0.3350 | 0.3329 |
76
- | 0.0023 | 10.7143 | 300 | 0.7469 | 0.3344 | 0.3294 |
77
- | 0.002 | 12.5 | 350 | 0.7677 | 0.3257 | 0.3217 |
78
- | 0.0009 | 14.2857 | 400 | 0.7667 | 0.3208 | 0.3182 |
79
- | 0.0009 | 16.0714 | 450 | 0.8388 | 0.3405 | 0.3388 |
80
- | 0.0031 | 17.8571 | 500 | 0.7991 | 0.3313 | 0.3323 |
81
- | 0.0003 | 19.6429 | 550 | 0.8032 | 0.3436 | 0.3406 |
82
- | 0.0002 | 21.4286 | 600 | 0.8200 | 0.3418 | 0.3400 |
83
- | 0.001 | 23.2143 | 650 | 0.8118 | 0.3436 | 0.3406 |
84
- | 0.0005 | 25.0 | 700 | 0.8278 | 0.3344 | 0.3323 |
85
- | 0.0007 | 26.7857 | 750 | 0.8299 | 0.3356 | 0.3318 |
86
- | 0.0006 | 28.5714 | 800 | 0.8390 | 0.3344 | 0.3318 |
87
- | 0.0004 | 30.3571 | 850 | 0.8442 | 0.3350 | 0.3323 |
88
- | 0.0002 | 32.1429 | 900 | 0.8444 | 0.3307 | 0.3294 |
89
- | 0.0005 | 33.9286 | 950 | 0.8549 | 0.3344 | 0.3329 |
90
- | 0.0007 | 35.7143 | 1000 | 0.8515 | 0.3331 | 0.3329 |
91
- | 0.0003 | 37.5 | 1050 | 0.8571 | 0.3263 | 0.3264 |
92
- | 0.0005 | 39.2857 | 1100 | 0.8504 | 0.3307 | 0.3294 |
93
- | 0.0001 | 41.0714 | 1150 | 0.8654 | 0.3313 | 0.3318 |
94
- | 0.0005 | 42.8571 | 1200 | 0.8724 | 0.3337 | 0.3347 |
95
- | 0.0001 | 44.6429 | 1250 | 0.8806 | 0.3325 | 0.3341 |
96
- | 0.0001 | 46.4286 | 1300 | 0.8901 | 0.3344 | 0.3359 |
97
- | 0.0001 | 48.2143 | 1350 | 0.8941 | 0.3344 | 0.3359 |
98
- | 0.0001 | 50.0 | 1400 | 0.8987 | 0.3337 | 0.3353 |
99
- | 0.0 | 51.7857 | 1450 | 0.9018 | 0.3337 | 0.3359 |
100
- | 0.0 | 53.5714 | 1500 | 0.9073 | 0.3325 | 0.3353 |
101
- | 0.0 | 55.3571 | 1550 | 0.9106 | 0.3319 | 0.3347 |
102
- | 0.0 | 57.1429 | 1600 | 0.9152 | 0.3319 | 0.3347 |
103
- | 0.0 | 58.9286 | 1650 | 0.9198 | 0.4824 | 0.4917 |
104
- | 0.0 | 60.7143 | 1700 | 0.9242 | 0.4824 | 0.4923 |
105
- | 0.0 | 62.5 | 1750 | 0.9279 | 0.4849 | 0.4947 |
106
- | 0.0 | 64.2857 | 1800 | 0.9327 | 0.4855 | 0.4953 |
107
- | 0.0 | 66.0714 | 1850 | 0.9374 | 0.4849 | 0.4953 |
108
- | 0.0 | 67.8571 | 1900 | 0.9417 | 0.4855 | 0.4965 |
109
- | 0.0 | 69.6429 | 1950 | 0.9461 | 0.4855 | 0.4965 |
110
- | 0.0 | 71.4286 | 2000 | 0.9507 | 0.4855 | 0.4965 |
111
 
112
 
113
  ### Framework versions
 
23
  metrics:
24
  - name: Wer
25
  type: wer
26
+ value: 0.33116883116883117
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.7091
37
+ - Wer Ortho: 0.3282
38
+ - Wer: 0.3312
39
 
40
  ## Model description
41
 
 
54
  ### Training hyperparameters
55
 
56
  The following hyperparameters were used during training:
57
+ - learning_rate: 2e-05
58
  - train_batch_size: 16
59
  - eval_batch_size: 16
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: constant_with_warmup
63
  - lr_scheduler_warmup_steps: 50
64
+ - training_steps: 500
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
70
  |:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|
71
+ | 1.1248 | 1.7857 | 50 | 0.5870 | 0.3868 | 0.3808 |
72
+ | 0.2048 | 3.5714 | 100 | 0.5389 | 0.3152 | 0.3129 |
73
+ | 0.0316 | 5.3571 | 150 | 0.6006 | 0.3233 | 0.3264 |
74
+ | 0.0083 | 7.1429 | 200 | 0.6418 | 0.3350 | 0.3359 |
75
+ | 0.0025 | 8.9286 | 250 | 0.6459 | 0.3276 | 0.3329 |
76
+ | 0.0012 | 10.7143 | 300 | 0.6761 | 0.3270 | 0.3294 |
77
+ | 0.0007 | 12.5 | 350 | 0.6790 | 0.3319 | 0.3335 |
78
+ | 0.0004 | 14.2857 | 400 | 0.6967 | 0.3313 | 0.3329 |
79
+ | 0.0008 | 16.0714 | 450 | 0.7005 | 0.3319 | 0.3347 |
80
+ | 0.0006 | 17.8571 | 500 | 0.7091 | 0.3282 | 0.3312 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
 
82
 
83
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f61c9dd0052da78fc48f9bb355c5cc5617ef59497059b16f95714d823f937e8
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6238ef4eb067ba2bc53d0f894781e353d812cecbd714588d538841b087774384
3
  size 151061672
runs/Oct02_21-43-30_dfd2db00b841/events.out.tfevents.1727905411.dfd2db00b841.1583.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bad4bc6379addf5f380c7ab68c5a9061c9612c1c041341da95cd18808e05700
3
- size 13819
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15f887e3df26fc45311b8816c96477bae2ba65df98679b6797974faa011c45e
3
+ size 14966