Training finished

README.md

@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2629
-- Wer: 380.3166
-- Cer: 297.4105
+- Loss: 0.2383
+- Wer: 449.4838
+- Cer: 314.1858
 
 ## Model description
 
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 8
+- num_epochs: 9
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -69,6 +69,7 @@ The following hyperparameters were used during training:
 | 0.3668        | 6.5714 | 100  | 146.0299 | 0.3359          | 242.0195 |
 | 0.3668        | 7.3175 | 110  | 217.5306 | 0.3022          | 297.0684 |
 | 0.3668        | 7.9524 | 120  | 280.9163 | 0.2764          | 312.5407 |
+| 0.3668        | 8.6349 | 130  | 0.2581   | 364.9837        | 232.8286 |
 
 
 ### Framework versions

runs/Feb13_19-28-17_ef6e562c574c/events.out.tfevents.1739475118.ef6e562c574c.31.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f12ded24cb1f2bd8bd7f4e79227960917a7e971d74bb522dfb0b495e2bd8399
+size 453