End of training

README.md

@@ -1,10 +1,10 @@
 ---
-base_model: facebook/wav2vec2-base
 license: apache-2.0
-metrics:
-- wer
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: 240615-wav2vec2-ASR-Arabs
   results: []
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2243
-- Wer: 0.6683
+- Loss: 1.5971
+- Wer: 0.2786
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 6.25  | 100  | 3.2243          | 0.6683 |
-| No log        | 12.5  | 200  | 3.4192          | 0.6699 |
-| No log        | 18.75 | 300  | 3.0514          | 0.6957 |
-| No log        | 25.0  | 400  | 2.9934          | 0.6715 |
+| No log        | 6.25  | 100  | 1.5971          | 0.2786 |
+| No log        | 12.5  | 200  | 1.5495          | 0.3188 |
+| No log        | 18.75 | 300  | 1.3824          | 0.3623 |
+| No log        | 25.0  | 400  | 1.4983          | 0.3575 |
 
 
 ### Framework versions