Hugging Face's logo

Frorozcol
/
whisper-small-dv

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Frorozcol commited on
Commit
bc003ec
•
1 Parent(s): 4f1b005

End of training

Browse files
Files changed (1) hide show
  1. README.md +9 -19
README.md CHANGED
@@ -16,13 +16,10 @@ model-index:
16
  dataset:
17
  name: PolyAI/minds14
18
  type: PolyAI/minds14
19
- config: en-US
20
- split: train
21
- args: en-US
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 39.352941176470594
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +29,9 @@ 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: 1.0162
36
- - Wer Ortho: 39.6669
37
- - Wer: 39.3529
38
 
39
  ## Model description
40
 
@@ -60,26 +57,19 @@ The following hyperparameters were used during training:
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: 4000
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
69
- |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
70
- | 0.0007 | 17.86 | 500 | 0.7824 | 37.8162 | 37.7647 |
71
- | 0.0002 | 35.71 | 1000 | 0.8518 | 37.8779 | 37.9412 |
72
- | 0.0001 | 53.57 | 1500 | 0.8928 | 38.6181 | 38.6471 |
73
- | 0.0001 | 71.43 | 2000 | 0.9228 | 38.2480 | 38.2353 |
74
- | 0.0 | 89.29 | 2500 | 0.9525 | 38.3097 | 38.2941 |
75
- | 0.0 | 107.14 | 3000 | 0.9759 | 38.9883 | 38.9412 |
76
- | 0.0 | 125.0 | 3500 | 0.9967 | 38.9266 | 38.8824 |
77
- | 0.0 | 142.86 | 4000 | 1.0162 | 39.6669 | 39.3529 |
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.35.2
83
  - Pytorch 2.1.0+cu121
84
- - Datasets 2.15.0
85
  - Tokenizers 0.15.0
 
16
  dataset:
17
  name: PolyAI/minds14
18
  type: PolyAI/minds14
 
 
 
19
  metrics:
20
  - name: Wer
21
  type: wer
22
+ value: 33.64544319600499
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.7041
33
+ - Wer Ortho: 33.8532
34
+ - Wer: 33.6454
35
 
36
  ## Model description
37
 
 
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: constant_with_warmup
59
  - lr_scheduler_warmup_steps: 50
60
+ - training_steps: 500
61
  - mixed_precision_training: Native AMP
62
 
63
  ### Training results
64
 
65
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
66
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
67
+ | 0.0015 | 17.86 | 500 | 0.7041 | 33.8532 | 33.6454 |
 
 
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
71
 
72
  - Transformers 4.35.2
73
  - Pytorch 2.1.0+cu121
74
+ - Datasets 2.16.0
75
  - Tokenizers 0.15.0