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_base
 tags:
 - generated_from_trainer
 metrics:
 - wer
 model-index:
-- name: Whisper base AR - BA
+- name: Graduation_Project_distillation_Whisper_base
   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_base
 
-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_base](https://huggingface.co/Baselhany/Graduation_Project_distillation_Whisper_base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0040
-- Wer: 0.0584
+- Loss: 0.0039
+- Wer: 0.0572
 
 ## Model description
 
@@ -49,28 +47,23 @@ 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: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer    |
-|:-------------:|:-------:|:----:|:---------------:|:------:|
-| 2.4566        | 1.0     | 469  | 0.0054          | 0.0643 |
-| 1.8089        | 2.0     | 938  | 0.0055          | 0.0607 |
-| 1.6333        | 3.0     | 1407 | 0.0054          | 0.0594 |
-| 1.3469        | 4.0     | 1876 | 0.0055          | 0.0639 |
-| 1.1481        | 5.0     | 2345 | 0.0053          | 0.0622 |
-| 0.9589        | 6.0     | 2814 | 0.0053          | 0.0672 |
-| 0.8766        | 7.0     | 3283 | 0.0052          | 0.0602 |
-| 0.8641        | 8.0     | 3752 | 0.0052          | 0.0626 |
-| 0.7951        | 9.0     | 4221 | 0.0053          | 0.0615 |
-| 0.7307        | 10.0    | 4690 | 0.0052          | 0.0605 |
-| 0.639         | 11.0    | 5159 | 0.0052          | 0.0617 |
-| 0.5802        | 12.0    | 5628 | 0.0052          | 0.0605 |
-| 0.5735        | 13.0    | 6097 | 0.0052          | 0.0628 |
-| 0.5273        | 14.0    | 6566 | 0.0052          | 0.0619 |
-| 0.4975        | 14.9685 | 7020 | 0.0052          | 0.0628 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 2.3799        | 1.0    | 285  | 0.0052          | 0.0603 |
+| 2.1095        | 2.0    | 570  | 0.0055          | 0.0638 |
+| 1.5385        | 3.0    | 855  | 0.0055          | 0.0624 |
+| 1.3712        | 4.0    | 1140 | 0.0054          | 0.0609 |
+| 1.1585        | 5.0    | 1425 | 0.0052          | 0.0613 |
+| 0.9381        | 6.0    | 1710 | 0.0051          | 0.0609 |
+| 0.8855        | 7.0    | 1995 | 0.0051          | 0.0598 |
+| 0.7963        | 8.0    | 2280 | 0.0051          | 0.0583 |
+| 0.6752        | 9.0    | 2565 | 0.0051          | 0.0605 |
+| 0.6299        | 9.9675 | 2840 | 0.0051          | 0.0617 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea86020b96c14789e8feda9f77212a513260794e19e8c7d312dd32402f2a7c0
+oid sha256:d59bb845f9d4f3d54f2cc31aea1f41adae0c59eb295bcdf332a0c288645c29cf
 size 223144592

runs/Jun22_16-50-40_a8cb5713fc9b/events.out.tfevents.1750622874.a8cb5713fc9b.19.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d592048e2dfb104aa3c9fac38f8a619eb4f3774c283370bcdc7b84881e8624
+size 406