sanchit-gandhi HF staff commited on
Commit
901ffa2
1 Parent(s): b567cce

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -7
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: 4.1637
19
- - Wer: 1.9677
20
 
21
  ## Model description
22
 
@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
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
@@ -51,9 +51,7 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
- | 4.1474 | 0.28 | 500 | 4.2554 | 1.9571 |
55
- | 4.5516 | 0.56 | 1000 | 4.1933 | 1.9631 |
56
- | 4.3244 | 0.84 | 1500 | 4.1637 | 1.9677 |
57
 
58
 
59
  ### 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: 4.2282
19
+ - Wer: 1.9681
20
 
21
  ## Model description
22
 
 
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
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
+ | 4.3268 | 0.56 | 500 | 4.2282 | 1.9681 |
 
 
55
 
56
 
57
  ### Framework versions