update model card README.md

README.md

@@ -12,15 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-korean-v3
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 1.2112
-- eval_wer: 0.4879
-- eval_runtime: 56.403
-- eval_samples_per_second: 10.194
-- eval_steps_per_second: 1.277
-- epoch: 23.08
-- step: 14100
+This model is a fine-tuned version of [Hyuk/wav2vec2-korean-v3](https://huggingface.co/Hyuk/wav2vec2-korean-v3) on the None dataset.
 
 ## Model description
 
@@ -48,7 +40,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 400
-- num_epochs: 100
+- num_epochs: 25
 - mixed_precision_training: Native AMP
 
 ### Framework versions