crossdelenna commited on
Commit
2a278d4
1 Parent(s): 5b8b5ef

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -6
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [crossdelenna/whisper-base.en](https://huggingface.co/crossdelenna/whisper-base.en) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0000
20
  - Wer: 0.1391
21
 
22
  ## Model description
@@ -43,17 +43,15 @@ The following hyperparameters were used during training:
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 500
46
- - training_steps: 2000
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
- | 0.0033 | 2.0 | 500 | 0.0051 | 0.4923 |
54
- | 0.0017 | 4.0 | 1000 | 0.0003 | 0.1713 |
55
- | 0.0001 | 6.0 | 1500 | 0.0001 | 0.1284 |
56
- | 0.0 | 8.0 | 2000 | 0.0000 | 0.1391 |
57
 
58
 
59
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [crossdelenna/whisper-base.en](https://huggingface.co/crossdelenna/whisper-base.en) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0001
20
  - Wer: 0.1391
21
 
22
  ## Model description
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 500
46
+ - training_steps: 1000
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 0.0008 | 2.0 | 500 | 0.0035 | 0.2248 |
54
+ | 0.0002 | 4.0 | 1000 | 0.0001 | 0.1391 |
 
 
55
 
56
 
57
  ### Framework versions