End of training

README.md

@@ -17,8 +17,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0049
-- Wer: 0.0
+- Loss: 0.1766
+- Wer: 22.7083
 
 ## Model description
 
@@ -53,13 +53,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 1.6257        | 1.6842 | 3    | 0.3394          | 23.8095 |
-| 0.1902        | 3.3684 | 6    | 0.0049          | 0.0     |
+| 2.4453        | 0.0163 | 3    | 0.4762          | 44.1146 |
+| 0.3891        | 0.0326 | 6    | 0.1766          | 22.7083 |
 
 
 ### Framework versions
 
-- Transformers 4.41.2
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.2
+- Transformers 4.42.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
 - Tokenizers 0.19.1

generation_config.json

@@ -236,5 +236,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.42.3"
 }