End of training

README.md

@@ -1,8 +1,10 @@
 ---
 license: apache-2.0
-base_model: openai/whisper-medium.en
+base_model: crossdelenna/whisper-medium.en
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: whisper-medium.en
   results: []
@@ -13,15 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-medium.en
 
-This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on an unknown dataset.
+This model is a fine-tuned version of [crossdelenna/whisper-medium.en](https://huggingface.co/crossdelenna/whisper-medium.en) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0764
-- eval_wer: 5.0889
-- eval_runtime: 810.2231
-- eval_samples_per_second: 1.274
-- eval_steps_per_second: 0.159
-- epoch: 2.0619
-- step: 800
+- Loss: 0.0303
+- Wer: 2.5444
 
 ## Model description
 
@@ -41,15 +38,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
-- training_steps: 1200
+- training_steps: 800
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.0838        | 0.5161 | 400  | 0.0678          | 5.0633 |
+| 0.0726        | 1.0323 | 800  | 0.0303          | 2.5444 |
+
+
 ### Framework versions
 
 - Transformers 4.43.0.dev0