End of training

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.4077568134171908
+      value: 0.40408805031446543
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8363
-- Wer Ortho: 0.4119
-- Wer: 0.4078
+- Loss: 0.9571
+- Wer Ortho: 0.4047
+- Wer: 0.4041
 
 ## Model description
 
@@ -57,14 +57,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 800
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
-| 0.0008        | 17.86 | 500  | 0.8363          | 0.4119    | 0.4078 |
+| 0.0           | 28.57 | 800  | 0.9571          | 0.4047    | 0.4041 |
 
 
 ### Framework versions