End of the training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: mayssakorbi/whisper-tiny-ar
+base_model: mayssakorbi/whisper-tiny-ar2
 tags:
 - generated_from_trainer
 datasets:
@@ -17,12 +17,12 @@ model-index:
       name: common_voice_16_1
       type: common_voice_16_1
       config: ar
-      split: test[:500]
+      split: test[500:1000]
       args: ar
     metrics:
     - name: Wer
       type: wer
-      value: 97.53747323340471
+      value: 92.15686274509804
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,11 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-tiny-ar2
 
-This model is a fine-tuned version of [mayssakorbi/whisper-tiny-ar](https://huggingface.co/mayssakorbi/whisper-tiny-ar) on the common_voice_16_1 dataset.
+This model is a fine-tuned version of [mayssakorbi/whisper-tiny-ar2](https://huggingface.co/mayssakorbi/whisper-tiny-ar2) on the common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0834
-- Wer Ortho: 82.1504
-- Wer: 97.5375
+- Loss: 0.9912
+- Wer Ortho: 77.8635
+- Wer: 92.1569
 
 ## Model description
 
@@ -69,7 +69,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.4733        | 0.4   | 50   | 1.0834          | 82.1504   | 97.5375 |
+| 0.5668        | 0.4   | 50   | 0.9912          | 77.8635   | 92.1569 |
 
 
 ### Framework versions

runs/May29_13-45-12_43fbc6e2297a/events.out.tfevents.1716990320.43fbc6e2297a.310.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d56161772175ac600c72b68e8707556fda2a2443ae3cca1c39be2f0f43c9bd42
-size 8017
+oid sha256:036f1d201805ee93598b16cff799427f6c4197f52c284f14dffdd7872dc09e6a
+size 8365