Training finished

README.md

@@ -21,8 +21,8 @@ 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: 0.0150
-- Wer: 13.4379
-- Cer: 4.1186
+- Wer: 13.4792
+- Cer: 4.1022
 
 ## 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: 19
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -184,18 +184,26 @@ The following hyperparameters were used during training:
 | 0.0006        | 17.6056 | 50000 | 4.0609  | 0.0149          | 13.3552  |
 | 0.0009        | 17.7464 | 50400 | 4.0827  | 0.0149          | 13.4406  |
 | 0.0007        | 17.8872 | 50800 | 4.0965  | 0.0149          | 13.4434  |
-| 0.0011        | 18.0282 | 51200 | 0.0150  | 13.4020         | 4.0696   |
-| 0.0007        | 18.1690 | 51600 | 0.0150  | 13.4516         | 4.0619   |
-| 0.0008        | 18.3098 | 52000 | 0.0150  | 13.3276         | 4.0388   |
-| 0.0009        | 18.4507 | 52400 | 0.0150  | 13.3414         | 4.0439   |
-| 0.001         | 18.5915 | 52800 | 0.0150  | 13.4406         | 4.0930   |
-| 0.0007        | 18.7323 | 53200 | 0.0150  | 13.4351         | 4.1163   |
-| 0.0008        | 18.8732 | 53600 | 0.0150  | 13.4379         | 4.1186   |
+| 0.0011        | 18.0282 | 51200 | 4.0696  | 0.0150          | 13.4020  |
+| 0.0007        | 18.1690 | 51600 | 4.0619  | 0.0150          | 13.4516  |
+| 0.0008        | 18.3098 | 52000 | 4.0388  | 0.0150          | 13.3276  |
+| 0.0009        | 18.4507 | 52400 | 4.0439  | 0.0150          | 13.3414  |
+| 0.001         | 18.5915 | 52800 | 4.0930  | 0.0150          | 13.4406  |
+| 0.0007        | 18.7323 | 53200 | 4.1163  | 0.0150          | 13.4351  |
+| 0.0008        | 18.8732 | 53600 | 4.1186  | 0.0150          | 13.4379  |
+| 0.001         | 19.0141 | 54000 | 0.0150  | 13.3965         | 4.0801   |
+| 0.0008        | 19.1549 | 54400 | 0.0151  | 13.4379         | 4.0984   |
+| 0.0008        | 19.2957 | 54800 | 0.0151  | 13.4186         | 4.1115   |
+| 0.0009        | 19.4366 | 55200 | 0.0150  | 13.3579         | 4.0622   |
+| 0.0009        | 19.5774 | 55600 | 0.0150  | 13.4103         | 4.0612   |
+| 0.0008        | 19.7182 | 56000 | 0.0150  | 13.4627         | 4.0769   |
+| 0.0009        | 19.8591 | 56400 | 0.0150  | 13.4819         | 4.1010   |
+| 0.0009        | 19.9999 | 56800 | 0.0150  | 13.4792         | 4.1022   |
 
 
 ### Framework versions
 
 - Transformers 4.47.0
 - Pytorch 2.5.1+cu121
-- Datasets 3.3.1
+- Datasets 3.2.0
 - Tokenizers 0.21.0