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 [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 19.2964
+- eval_loss: 3.7793
 - eval_wer: 1.0
-- eval_runtime: 2.1277
-- eval_samples_per_second: 9.4
-- eval_steps_per_second: 1.41
-- epoch: 4.0
-- step: 20
+- eval_runtime: 2.4007
+- eval_samples_per_second: 8.331
+- eval_steps_per_second: 1.25
+- epoch: 24.0
+- step: 120
 
 ## Model description