sanchit-gandhi HF staff commited on
Commit
b98be8f
1 Parent(s): 85f5a69

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -6
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 4.1969
19
- - Wer: 1.9248
20
 
21
  ## Model description
22
 
@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
39
  - train_batch_size: 12
40
  - eval_batch_size: 12
41
  - seed: 42
42
- - gradient_accumulation_steps: 2
43
- - total_train_batch_size: 24
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
@@ -51,8 +51,7 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
- | 4.4141 | 0.42 | 500 | 4.3002 | 1.9045 |
55
- | 4.4466 | 0.84 | 1000 | 4.1969 | 1.9248 |
56
 
57
 
58
  ### Framework versions
 
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: 4.1996
19
+ - Wer: 1.9704
20
 
21
  ## Model description
22
 
 
39
  - train_batch_size: 12
40
  - eval_batch_size: 12
41
  - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 48
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 4.3531 | 0.84 | 500 | 4.1996 | 1.9704 |
 
55
 
56
 
57
  ### Framework versions