Model save

README.md

@@ -1,27 +1,25 @@
 ---
 library_name: transformers
-language:
-- ar
 license: apache-2.0
-base_model: openai/whisper-base
+base_model: Baselhany/Graduation_Project_distillation_Whisper_base2
 tags:
 - generated_from_trainer
 metrics:
 - wer
 model-index:
-- name: Whisper base AR - BA
+- name: Graduation_Project_distillation_Whisper_base2
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper base AR - BA
+# Graduation_Project_distillation_Whisper_base2
 
-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.
+This model is a fine-tuned version of [Baselhany/Graduation_Project_distillation_Whisper_base2](https://huggingface.co/Baselhany/Graduation_Project_distillation_Whisper_base2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1026
-- Wer: 0.2760
+- Loss: 0.1097
+- Wer: 0.2742
 
 ## Model description
 
@@ -49,28 +47,18 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 15
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer    |
-|:-------------:|:-------:|:----:|:---------------:|:------:|
-| 1.2205        | 0.9987  | 595  | 0.0773          | 0.2691 |
-| 0.7481        | 1.9987  | 1190 | 0.0850          | 0.3144 |
-| 0.4781        | 2.9987  | 1785 | 0.0928          | 0.2558 |
-| 0.338         | 3.9987  | 2380 | 0.0905          | 0.2638 |
-| 0.2998        | 4.9987  | 2975 | 0.0881          | 0.3087 |
-| 0.1988        | 5.9987  | 3570 | 0.0934          | 0.2822 |
-| 0.155         | 6.9987  | 4165 | 0.0865          | 0.2979 |
-| 0.1536        | 7.9987  | 4760 | 0.0894          | 0.2806 |
-| 0.1456        | 8.9987  | 5355 | 0.0867          | 0.3210 |
-| 0.1205        | 9.9987  | 5950 | 0.0868          | 0.3017 |
-| 0.087         | 10.9987 | 6545 | 0.0880          | 0.2926 |
-| 0.0673        | 11.9987 | 7140 | 0.0859          | 0.2944 |
-| 0.0683        | 12.9987 | 7735 | 0.0887          | 0.2996 |
-| 0.0474        | 13.9987 | 8330 | 0.0876          | 0.2974 |
-| 0.0406        | 14.9987 | 8925 | 0.0886          | 0.2991 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.3035        | 0.9987 | 595  | 0.0981          | 0.2460 |
+| 0.2664        | 1.9987 | 1190 | 0.0935          | 0.2819 |
+| 0.2242        | 2.9987 | 1785 | 0.0878          | 0.2786 |
+| 0.1442        | 3.9987 | 2380 | 0.0873          | 0.2561 |
+| 0.1145        | 4.9987 | 2975 | 0.0848          | 0.2558 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44cfa7b426aff9c6f55efd8c8db8807dea2f6f78a7cf19371d209d9bed81362
+oid sha256:c52bd2321d3a6d973bd18d2f7edb573ec2184d670ffeddd333d500a3daf46653
 size 223144592

runs/Jun20_20-34-49_83d86f13a4a6/events.out.tfevents.1750464270.83d86f13a4a6.19.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7adab8c8a523247b3c2a5f2599d0e336f2e28619763fa1794cb16d2d4a14846e
+size 406