Model save

README.md

@@ -1,27 +1,28 @@
 ---
 library_name: transformers
-language:
-- ar
 license: apache-2.0
-base_model: openai/whisper-base
+base_model: Baselhany/Graduation_Project_Distilation_Whisper_base3
 tags:
 - generated_from_trainer
-metrics:
-- wer
 model-index:
-- name: Whisper base AR - BA
+- name: Graduation_Project_Distilation_Whisper_base3
   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_Distilation_Whisper_base3
 
-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_Distilation_Whisper_base3](https://huggingface.co/Baselhany/Graduation_Project_Distilation_Whisper_base3) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0890
-- Wer: 0.1942
+- eval_loss: 0.0292
+- eval_model_preparation_time: 0.0028
+- eval_wer: 0.0968
+- eval_runtime: 784.1659
+- eval_samples_per_second: 3.826
+- eval_steps_per_second: 0.478
+- step: 0
 
 ## Model description
 
@@ -49,38 +50,12 @@ 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: 20
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch   | Step | Validation Loss | Wer    |
-|:-------------:|:-------:|:----:|:---------------:|:------:|
-| 1.7224        | 1.0     | 301  | 0.0867          | 0.1888 |
-| 1.6242        | 2.0     | 602  | 0.0876          | 0.1970 |
-| 1.3485        | 3.0     | 903  | 0.0880          | 0.1932 |
-| 1.2337        | 4.0     | 1204 | 0.0895          | 0.1872 |
-| 1.0669        | 5.0     | 1505 | 0.0861          | 0.1932 |
-| 1.0507        | 6.0     | 1806 | 0.0855          | 0.1829 |
-| 0.9844        | 7.0     | 2107 | 0.0861          | 0.1892 |
-| 0.8618        | 8.0     | 2408 | 0.0844          | 0.1873 |
-| 0.7956        | 9.0     | 2709 | 0.0849          | 0.1964 |
-| 0.7654        | 10.0    | 3010 | 0.0842          | 0.1895 |
-| 0.6957        | 11.0    | 3311 | 0.0843          | 0.1848 |
-| 0.7042        | 12.0    | 3612 | 0.0837          | 0.1866 |
-| 0.6364        | 13.0    | 3913 | 0.0831          | 0.1929 |
-| 0.6357        | 14.0    | 4214 | 0.0829          | 0.1895 |
-| 0.6137        | 15.0    | 4515 | 0.0827          | 0.1904 |
-| 0.5909        | 16.0    | 4816 | 0.0824          | 0.1904 |
-| 0.5582        | 17.0    | 5117 | 0.0823          | 0.1941 |
-| 0.5409        | 18.0    | 5418 | 0.0824          | 0.1916 |
-| 0.5305        | 19.0    | 5719 | 0.0823          | 0.1895 |
-| 0.5137        | 19.9343 | 6000 | 0.0824          | 0.1902 |
-
-
 ### Framework versions
 
-- Transformers 4.51.3
-- Pytorch 2.6.0+cu124
-- Datasets 3.6.0
-- Tokenizers 0.21.1
+- Transformers 4.51.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.0

config.json

@@ -53,7 +53,7 @@
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.51.1",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -208,7 +208,7 @@
   "tie_word_embeddings": true,
   "tokenizer_class": null,
   "torchscript": false,
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.51.1",
   "use_bfloat16": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

runs/Jun23_14-04-30_622dd1a6c211/events.out.tfevents.1750688255.622dd1a6c211.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef949d0c92e2ba648f2b06ff9cfe4a54ede9d48114ae9049dfe88c67aa15c76d
+size 404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01bd6b74ff3330c40b66014b7a8633f14d2e802969473d23195377f8dfda4e6c
+oid sha256:789f58b69a0f91dab5c8b603a740843d5ecea78923fcf90739cac1ee6262547c
 size 5496