End of training

README.md

@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the customd_ataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6329
-- Cer: 135.4273
+- Loss: 0.5808
+- Cer: 75.3104
 
 ## Model description
 
@@ -52,10 +52,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Cer      |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.2371        | 1.0   | 113  | 0.6409          | 112.3448 |
-| 0.1295        | 2.0   | 226  | 0.6329          | 135.4273 |
+| Training Loss | Epoch | Step | Validation Loss | Cer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.5999        | 1.0   | 113  | 0.6111          | 49.3061 |
+| 0.2814        | 2.0   | 226  | 0.5808          | 75.3104 |
 
 
 ### Framework versions