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: 0.0041
-- Wer: 0.0612
+- Loss: 0.0040
+- Wer: 0.0613
 
 ## 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    |
-|:-------------:|:-------:|:----:|:---------------:|:------:|
-| 0.9062        | 1.0     | 469  | 0.0057          | 0.0711 |
-| 0.5562        | 2.0     | 938  | 0.0060          | 0.0740 |
-| 0.455         | 3.0     | 1407 | 0.0060          | 0.0730 |
-| 0.2991        | 4.0     | 1876 | 0.0059          | 0.0706 |
-| 0.2373        | 5.0     | 2345 | 0.0058          | 0.0711 |
-| 0.1748        | 6.0     | 2814 | 0.0055          | 0.0692 |
-| 0.1492        | 7.0     | 3283 | 0.0056          | 0.0653 |
-| 0.1477        | 8.0     | 3752 | 0.0055          | 0.0672 |
-| 0.1326        | 9.0     | 4221 | 0.0055          | 0.0683 |
-| 0.1169        | 10.0    | 4690 | 0.0054          | 0.0700 |
-| 0.083         | 11.0    | 5159 | 0.0054          | 0.0677 |
-| 0.0696        | 12.0    | 5628 | 0.0054          | 0.0653 |
-| 0.0614        | 13.0    | 6097 | 0.0053          | 0.0681 |
-| 0.0457        | 14.0    | 6566 | 0.0053          | 0.0655 |
-| 0.0383        | 14.9685 | 7020 | 0.0053          | 0.0643 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.75          | 1.0    | 285  | 0.0051          | 0.0655 |
+| 0.6367        | 2.0    | 570  | 0.0057          | 0.0711 |
+| 0.3656        | 3.0    | 855  | 0.0055          | 0.0677 |
+| 0.2944        | 4.0    | 1140 | 0.0057          | 0.0719 |
+| 0.2291        | 5.0    | 1425 | 0.0053          | 0.0656 |
+| 0.1613        | 6.0    | 1710 | 0.0053          | 0.0655 |
+| 0.1531        | 7.0    | 1995 | 0.0052          | 0.0670 |
+| 0.1173        | 8.0    | 2280 | 0.0051          | 0.0708 |
+| 0.0836        | 9.0    | 2565 | 0.0051          | 0.0704 |
+| 0.065         | 9.9675 | 2840 | 0.0051          | 0.0681 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd08a51445ecf23bf7250a37ed5c96d12fdcabb18711863fd118f51a3185e3fe
+oid sha256:a44c051ec558b2169b8ecef070c34b4f5b6af451eac4f971d3dfaeb64037541f
 size 223144592

runs/Jun22_16-47-33_39deb02e5a0e/events.out.tfevents.1750622597.39deb02e5a0e.19.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85aea33b7a3c7da78ed1d9a2606284525f1feccc418a8c5a17aa87f43431e2b2
+size 406