Training in progress, step 3900

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-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.4503
-- eval_wer: 71.7241
-- eval_runtime: 147.162
-- eval_samples_per_second: 0.68
-- eval_steps_per_second: 0.02
-- epoch: 10.8860
-- step: 3600
+- eval_loss: 0.4610
+- eval_wer: 71.0345
+- eval_runtime: 143.56
+- eval_samples_per_second: 0.697
+- eval_steps_per_second: 0.021
+- epoch: 11.8632
+- step: 3900
 
 ## Model description