Training finished

README.md

@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0735
-- Wer: 0.4484
+- Loss: 0.0984
+- Wer: 0.4063
 
 ## Model description
 
@@ -56,14 +56,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.0542        | 2.5   | 100  | 0.0660          | 0.4615 |
-| 0.0203        | 5.0   | 200  | 0.0735          | 0.4484 |
-| 0.006         | 7.5   | 300  | 0.0850          | 0.4641 |
-| 0.0127        | 10.0  | 400  | 0.0923          | 0.5380 |
-| 0.0107        | 12.5  | 500  | 0.0984          | 0.5805 |
-| 0.0054        | 15.0  | 600  | 0.0979          | 0.4676 |
-| 0.0004        | 17.5  | 700  | 0.0944          | 0.4393 |
-| 0.0001        | 20.0  | 800  | 0.0940          | 0.4529 |
+| 0.0375        | 2.5   | 100  | 0.0710          | 0.4562 |
+| 0.0153        | 5.0   | 200  | 0.0825          | 0.4610 |
+| 0.0068        | 7.5   | 300  | 0.0952          | 0.5871 |
+| 0.0132        | 10.0  | 400  | 0.1040          | 0.6013 |
+| 0.0093        | 12.5  | 500  | 0.1091          | 0.5994 |
+| 0.0042        | 15.0  | 600  | 0.1018          | 0.4415 |
+| 0.0005        | 17.5  | 700  | 0.0994          | 0.4286 |
+| 0.0001        | 20.0  | 800  | 0.0984          | 0.4063 |
 
 
 ### Framework versions

runs/Dec11_17-07-31_fb7c0e836fe0/events.out.tfevents.1733939672.fb7c0e836fe0.23.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c836d9edb6268c3bae4fb27623fb2f66dd27fff606e8c988e2e8525cd549ad
+size 406