Hugging Face's logo

vineetsharma
/
whisper-tiny-finetuned-minds14-en-v2

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
vineetsharma commited on
Commit
7cbb589
·
1 Parent(s): fae2d39

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -15
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Wer
23
  type: wer
24
- value: 0.34297520661157027
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,9 +31,9 @@ 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 PolyAI/minds14 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.6386
35
- - Wer Ortho: 0.3461
36
- - Wer: 0.3430
37
 
38
  ## Model description
39
 
@@ -59,22 +59,18 @@ The following hyperparameters were used during training:
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: constant_with_warmup
61
  - lr_scheduler_warmup_steps: 50
62
- - training_steps: 500
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
68
- | 1.7971 | 1.79 | 50 | 0.7476 | 0.4411 | 0.4008 |
69
- | 0.3112 | 3.57 | 100 | 0.4953 | 0.3560 | 0.3453 |
70
- | 0.1214 | 5.36 | 150 | 0.5073 | 0.3763 | 0.3589 |
71
- | 0.0359 | 7.14 | 200 | 0.5244 | 0.3442 | 0.3347 |
72
- | 0.011 | 8.93 | 250 | 0.5569 | 0.3510 | 0.3371 |
73
- | 0.0038 | 10.71 | 300 | 0.5903 | 0.3393 | 0.3329 |
74
- | 0.0019 | 12.5 | 350 | 0.6068 | 0.3405 | 0.3353 |
75
- | 0.0012 | 14.29 | 400 | 0.6175 | 0.3418 | 0.3377 |
76
- | 0.0012 | 16.07 | 450 | 0.6253 | 0.3362 | 0.3329 |
77
- | 0.0013 | 17.86 | 500 | 0.6386 | 0.3461 | 0.3430 |
78
 
79
 
80
  ### Framework versions
 
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 0.33530106257378983
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 PolyAI/minds14 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.6804
35
+ - Wer Ortho: 0.3362
36
+ - Wer: 0.3353
37
 
38
  ## Model description
39
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: constant_with_warmup
61
  - lr_scheduler_warmup_steps: 50
62
+ - training_steps: 300
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
68
+ | 0.0014 | 1.79 | 50 | 0.6437 | 0.3708 | 0.3648 |
69
+ | 0.0012 | 3.57 | 100 | 0.6664 | 0.3461 | 0.3353 |
70
+ | 0.0113 | 5.36 | 150 | 0.6338 | 0.3374 | 0.3353 |
71
+ | 0.0021 | 7.14 | 200 | 0.6466 | 0.3467 | 0.3453 |
72
+ | 0.0013 | 8.93 | 250 | 0.6690 | 0.3399 | 0.3383 |
73
+ | 0.0006 | 10.71 | 300 | 0.6804 | 0.3362 | 0.3353 |
 
 
 
 
74
 
75
 
76
  ### Framework versions