Commit
•
c5516e0
1
Parent(s):
608609a
update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,9 +14,6 @@ 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 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 5.2175
|
| 19 |
-
- Wer: 2.0223
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -39,8 +36,8 @@ The following hyperparameters were used during training:
|
|
| 39 |
- train_batch_size: 12
|
| 40 |
- eval_batch_size: 12
|
| 41 |
- seed: 42
|
| 42 |
-
- gradient_accumulation_steps:
|
| 43 |
-
- total_train_batch_size:
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 500
|
|
@@ -49,9 +46,6 @@ The following hyperparameters were used during training:
|
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
-
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
-
| 4.8633 | 0.84 | 500 | 5.2175 | 2.0223 |
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
| 14 |
#
|
| 15 |
|
| 16 |
This model was trained from scratch on the librispeech_asr dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
| 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 |
|
| 47 |
### Training results
|
| 48 |
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
|
| 51 |
### Framework versions
|