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-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 5.6532
-- eval_wer: 167.5926
-- eval_runtime: 240.5003
-- eval_samples_per_second: 0.166
-- eval_steps_per_second: 0.012
-- epoch: 2.96
-- step: 34
+- eval_loss: 1.8891
+- eval_wer: 109.2227
+- eval_runtime: 1248.533
+- eval_samples_per_second: 0.195
+- eval_steps_per_second: 0.013
+- epoch: 1.0
+- step: 138
 
 ## Model description
 
@@ -43,12 +43,10 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1000
-- training_steps: 500
+- lr_scheduler_warmup_steps: 500
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Framework versions