Update README.md

README.md

@@ -45,26 +45,30 @@ It achieves the following results on the evaluation set:
 - Loss: 0.5362
 - Wer: 58.5848
 
-## Model description
+## Example of usage:
+```
+from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
 
-More information needed
+processor = AutoProcessor.from_pretrained("Salama1429/KalemaTech-Arabic-STT-ASR-based-on-Whisper-Small")
 
+model = AutoModelForSpeechSeq2Seq.from_pretrained("Salama1429/KalemaTech-Arabic-STT-ASR-based-on-Whisper-Small")
+```
 ## Intended uses & limitations
 
-More information needed
+Automatic Speech Recognition
 
 ## Training and evaluation data
-
+```
 Common_Voice_Arabic_12.0 and I made some augmentations to it as follows:
 - 25% of the data TimeMasking
 - 25% of the data SpecAugmentation
 - 25% of the data WavAugmentation (AddGaussianNoise)
 - The final dataset is the original common voice plus the augmented files
-
+```
 ## Training procedure
 
 ### Training hyperparameters
-
+```
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 64
@@ -75,7 +79,7 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 25
 - mixed_precision_training: Native AMP
-
+```
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Wer     |