End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 52.3565728053004
+      value: 34.49781659388647
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the zeroth-korean dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0884
-- Wer: 52.3566
+- Loss: 0.1071
+- Wer: 34.4978
 
 ## Model description
 
@@ -54,7 +54,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -66,9 +66,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0254        | 0.36  | 1000 | 0.1079          | 35.4314 |
-| 0.0141        | 0.72  | 2000 | 0.0955          | 41.0029 |
-| 0.0097        | 1.08  | 3000 | 0.0884          | 52.3566 |
+| 0.0586        | 0.18  | 1000 | 0.1426          | 23.0236 |
+| 0.0323        | 0.36  | 2000 | 0.1189          | 27.9777 |
+| 0.028         | 0.54  | 3000 | 0.1071          | 34.4978 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb3d10286b173ef55c967686f83ad819e5b70121de303fefa2967232fd6e7063
+oid sha256:f0f70a6b6f5316513f6c47abae79a3ba85cd5897b3c1d0d20c12f8367364f344
 size 967102729