sanchit-gandhi HF staff commited on
Commit
56a3e16
1 Parent(s): b53b675

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -5
README.md CHANGED
@@ -14,6 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
14
  #
15
 
16
  This model was trained from scratch on the librispeech_asr dataset.
 
 
 
17
 
18
  ## Model description
19
 
@@ -32,12 +35,12 @@ More information needed
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
- - learning_rate: 0.0003
36
- - train_batch_size: 12
37
- - eval_batch_size: 12
38
  - seed: 42
39
- - gradient_accumulation_steps: 8
40
- - total_train_batch_size: 96
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 500
@@ -46,6 +49,11 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
 
 
 
 
 
49
 
50
 
51
  ### Framework versions
 
14
  #
15
 
16
  This model was trained from scratch on the librispeech_asr dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 5.1729
19
+ - Wer: 1.9734
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.001
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
  - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 16
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 5.5553 | 0.28 | 500 | 5.9849 | 1.9268 |
55
+ | 5.1997 | 0.56 | 1000 | 5.6568 | 1.9540 |
56
+ | 4.996 | 0.84 | 1500 | 5.1729 | 1.9734 |
57
 
58
 
59
  ### Framework versions