Update README.md

README.md

@@ -75,20 +75,6 @@ As you can see, my model performs better in maximum case :D
 
 ## Training procedure
 
-#### Model hyperparameters
-```python
-model = Wav2Vec2ForCTC.from_pretrained(
-    model_name_or_path if not last_checkpoint else last_checkpoint,
-    # hp-mehrdad: Hyperparams of 'm3hrdadfi/wav2vec2-large-xlsr-persian-v3'
-    attention_dropout = 0.05316,
-    hidden_dropout    = 0.01941,
-    feat_proj_dropout = 0.01249,
-    mask_time_prob    = 0.04529,
-    layerdrop         = 0.01377,
-    ctc_loss_reduction = 'mean',
-    ctc_zero_infinity = True,
-)
-```
 #### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -133,7 +119,7 @@ The following hyperparameters were used during training:
 Several models with differet hyperparameters were trained. The following figures show the training process for three of them.
 ![wer](wandb-wer.png)
 ![loss](wandb-loss.png)
-'20_2000_1e-5_hp-mehrdad' is the current model and it's hyperparameter are:
+'20_2000_1e-5_hp-mehrdad' is the current model and it's hyperparameters are:
 ```python
 model = Wav2Vec2ForCTC.from_pretrained(
     model_name_or_path if not last_checkpoint else last_checkpoint,
@@ -146,8 +132,6 @@ model = Wav2Vec2ForCTC.from_pretrained(
     ctc_loss_reduction = 'mean',
     ctc_zero_infinity = True,
 )
-
-learning_rate = 1e-5
 ```
 The hyperparameters of '19_2000_1e-5_hp-base' are:
 ```python
@@ -162,8 +146,6 @@ model = Wav2Vec2ForCTC.from_pretrained(
     ctc_loss_reduction = 'mean',
     ctc_zero_infinity = True,
 )
-
-learing_rate = 1e-5
 ```
 
 And the hyperparameters of '22_2000_1e-5_hp-masoud' are:
@@ -179,9 +161,8 @@ model = Wav2Vec2ForCTC.from_pretrained(
 	ctc_loss_reduction = 'mean',
 	ctc_zero_infinity = True,
 )
-
-learning_rate = 1e-5
 ```
+Learning rate is 1e-5 for all three models.
 As you can see this model performs better with WER metric on validation(evaluation) set.
 
 #### Framework versions