update model card README.md

README.md

@@ -16,13 +16,13 @@ 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 tamil_eng_data dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.3225
-- eval_wer: 408.5725
-- eval_runtime: 346.6466
-- eval_samples_per_second: 2.094
+- eval_loss: 3.4139
+- eval_wer: 377.6215
+- eval_runtime: 345.7586
+- eval_samples_per_second: 2.1
 - eval_steps_per_second: 0.133
-- epoch: 13.02
-- step: 400
+- epoch: 16.04
+- step: 500
 
 ## Model description