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-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1553
-- Wer: 67.5872
+- Loss: 1.4290
+- Wer: 70.8531
 
 ## Model description
 
@@ -56,8 +56,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 1.878         | 0.0   | 1    | 2.1553          | 67.5872 |
-| 2.007         | 0.01  | 2    | 2.1553          | 67.5872 |
+| 2.2022        | 0.04  | 1    | 2.1401          | 70.6161 |
+| 2.3838        | 0.09  | 2    | 1.4290          | 70.8531 |
 
 
 ### Framework versions

runs/Nov10_09-57-52_e09696c72a99/events.out.tfevents.1699610276.e09696c72a99

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51b7688c3919a46f6adfb9f4c1e63c7bb39eedaddbc3eb8d433ee95a477592e
-size 5492
+oid sha256:533e8e0838f96d9facd8e2348e79bf5c51a2809758f42d1dc045be1858c6814b
+size 6306