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: 0.2451
-- eval_wer: 43.3301
-- eval_runtime: 69.3375
-- eval_samples_per_second: 1.442
-- eval_steps_per_second: 0.029
-- epoch: 2.03
-- step: 4500
+- eval_loss: 0.2455
+- eval_wer: 42.6485
+- eval_runtime: 74.0826
+- eval_samples_per_second: 1.35
+- eval_steps_per_second: 0.027
+- epoch: 2.13
+- step: 5000
 
 ## Model description