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 10th_science_tamil_to_english dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 4.1630
-- eval_wer: 144.0196
-- eval_runtime: 193.3064
-- eval_samples_per_second: 2.007
-- eval_steps_per_second: 0.129
-- epoch: 15.01
-- step: 4200
+- eval_loss: 4.1847
+- eval_wer: 175.7103
+- eval_runtime: 219.4087
+- eval_samples_per_second: 1.768
+- eval_steps_per_second: 0.114
+- epoch: 7.01
+- step: 4500
 
 ## Model description
 
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 - 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: 1400
+- lr_scheduler_warmup_steps: 500
 - training_steps: 5000
 - mixed_precision_training: Native AMP