End of training

README.md

@@ -18,6 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 # Whisper Small Korean
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 17.0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4655
+- Cer: 12.5288
 
 ## Model description
 
@@ -37,8 +40,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 64
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -46,6 +49,14 @@ The following hyperparameters were used during training:
 - training_steps: 1000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Cer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 0.0063        | 11.1111 | 500  | 0.4418          | 12.3382 |
+| 0.0011        | 22.2222 | 1000 | 0.4655          | 12.5288 |
+
+
 ### Framework versions
 
 - Transformers 4.42.3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c194528f0bbd9472ee8e791709e9bcdf9b280f87114cd4e0109fc1ddf25d07ac
+oid sha256:cb6bfd05e49452662ce4f680b95889ecce0c793f6c84848e1e6ec8d5bcfffecd
 size 966995080