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: 0.2720
-- eval_wer: 47.5657
-- eval_runtime: 78.0972
-- eval_samples_per_second: 1.28
-- eval_steps_per_second: 0.026
-- epoch: 0.4
-- step: 2000
+- eval_loss: 0.2632
+- eval_wer: 45.2288
+- eval_runtime: 68.5355
+- eval_samples_per_second: 1.459
+- eval_steps_per_second: 0.029
+- epoch: 1.06
+- step: 2500
 
 ## Model description