update model card README.md

README.md

@@ -14,13 +14,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2519
-- eval_wer: 44.5959
-- eval_runtime: 68.631
-- eval_samples_per_second: 1.457
+- eval_loss: 0.2475
+- eval_wer: 43.7196
+- eval_runtime: 67.9563
+- eval_samples_per_second: 1.472
 - eval_steps_per_second: 0.029
-- epoch: 1.26
-- step: 3500
+- epoch: 1.36
+- step: 4000
 
 ## Model description