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-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.3973
-- eval_wer: 61.9279
-- eval_runtime: 62.6118
-- eval_samples_per_second: 1.597
-- eval_steps_per_second: 0.048
-- epoch: 0.7
-- step: 2100
+- eval_loss: 0.3908
+- eval_wer: 61.5385
+- eval_runtime: 61.0288
+- eval_samples_per_second: 1.639
+- eval_steps_per_second: 0.049
+- epoch: 0.8
+- step: 2400
 
 ## Model description