Update README.md
Browse files
README.md
CHANGED
@@ -129,6 +129,11 @@ The following hyperparameters were used during training:
|
|
129 |
| 0.8238 | 11.88 | 1900 | 0.6735 | 0.3297 |
|
130 |
| 0.7618 | 12.5 | 2000 | 0.6728 | 0.3286 |
|
131 |
|
|
|
|
|
|
|
|
|
|
|
132 |
|
133 |
#### Framework versions
|
134 |
|
|
|
129 |
| 0.8238 | 11.88 | 1900 | 0.6735 | 0.3297 |
|
130 |
| 0.7618 | 12.5 | 2000 | 0.6728 | 0.3286 |
|
131 |
|
132 |
+
#### Choosing the best model
|
133 |
+
Several models with differet hyperparameters were trained. The following figures show the training process for three of them.
|
134 |
+
![wer](wandb-wer.jpg)
|
135 |
+
![loss](wandb-loss.jpg)
|
136 |
+
As you can see this model performs better of evaluation set.
|
137 |
|
138 |
#### Framework versions
|
139 |
|