End of training

README.md

@@ -18,9 +18,9 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6691
-- Wer Ortho: 73.1332
-- Wer: 73.1148
+- Loss: 0.4842
+- Wer Ortho: 60.9132
+- Wer: 60.9029
 
 ## Model description
 
@@ -46,19 +46,22 @@ 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: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
-| 0.8185        | 2.4752 | 500  | 0.6691          | 73.1332   | 73.1148 |
+| 1.0053        | 1.5198 | 500  | 0.6511          | 72.9011   | 72.8777 |
+| 0.7337        | 3.0395 | 1000 | 0.5380          | 65.5752   | 65.5485 |
+| 0.5557        | 4.5593 | 1500 | 0.4971          | 63.5066   | 63.4855 |
+| 0.3969        | 6.0790 | 2000 | 0.4842          | 60.9132   | 60.9029 |
 
 
 ### Framework versions
 
-- Transformers 4.52.4
+- Transformers 4.51.3
 - Pytorch 2.6.0+cu124
 - Datasets 3.6.0
 - Tokenizers 0.21.2

generation_config.json

@@ -235,5 +235,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.52.4"
+  "transformers_version": "4.51.3"
 }