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/Distilation_Whisper_base_bigger_samples
 tags:
 - generated_from_trainer
 metrics:
 - wer
 model-index:
-- name: Whisper base AR - BA
+- name: Distilation_Whisper_base_bigger_samples
   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
+# Distilation_Whisper_base_bigger_samples
 
-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/Distilation_Whisper_base_bigger_samples](https://huggingface.co/Baselhany/Distilation_Whisper_base_bigger_samples) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0907
-- Wer: 0.1967
+- Loss: 0.0931
+- Wer: 0.1960
 
 ## Model description
 
@@ -49,23 +47,28 @@ 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: 10
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 2.1766        | 1.0   | 625  | 0.0940          | 0.2060 |
-| 1.8382        | 2.0   | 1250 | 0.0916          | 0.1966 |
-| 1.4337        | 3.0   | 1875 | 0.0906          | 0.1905 |
-| 1.2601        | 4.0   | 2500 | 0.0898          | 0.1904 |
-| 1.1154        | 5.0   | 3125 | 0.0884          | 0.1886 |
-| 1.0993        | 6.0   | 3750 | 0.0875          | 0.1902 |
-| 0.9665        | 7.0   | 4375 | 0.0866          | 0.1936 |
-| 0.9165        | 8.0   | 5000 | 0.0866          | 0.1929 |
-| 0.8476        | 9.0   | 5625 | 0.0865          | 0.1926 |
-| 0.7916        | 10.0  | 6250 | 0.0865          | 0.1927 |
+| 1.8752        | 1.0   | 457  | 0.0914          | 0.2050 |
+| 1.8589        | 2.0   | 914  | 0.0902          | 0.1879 |
+| 1.4408        | 3.0   | 1371 | 0.0905          | 0.2060 |
+| 1.3046        | 4.0   | 1828 | 0.0886          | 0.1908 |
+| 1.1751        | 5.0   | 2285 | 0.0870          | 0.2003 |
+| 1.0567        | 6.0   | 2742 | 0.0882          | 0.1955 |
+| 0.9915        | 7.0   | 3199 | 0.0867          | 0.1950 |
+| 0.91          | 8.0   | 3656 | 0.0875          | 0.2004 |
+| 0.8595        | 9.0   | 4113 | 0.0858          | 0.2093 |
+| 0.7878        | 10.0  | 4570 | 0.0863          | 0.2019 |
+| 0.7881        | 11.0  | 5027 | 0.0854          | 0.1983 |
+| 0.7512        | 12.0  | 5484 | 0.0853          | 0.2053 |
+| 0.7167        | 13.0  | 5941 | 0.0853          | 0.2054 |
+| 0.683         | 14.0  | 6398 | 0.0850          | 0.1995 |
+| 0.6468        | 15.0  | 6855 | 0.0851          | 0.1986 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae7606038ed41d9f54150c607563af1e0b7e37ba6fa4835806cd1c8dcccc654
+oid sha256:7d7b4badba29f69c647fcd5fe48898b278b29767819baeaa9525e7d13d1f30bb
 size 223144592

runs/Jun02_04-35-50_581b6451c54e/events.out.tfevents.1748865288.581b6451c54e.19.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586a46cf0100799652d64cbf303b065e3af53ed2c9deadc6705857d1f9daa9df
+size 406