End of training

README.md

@@ -21,8 +21,8 @@ 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: 0.2549
-- Wer: 98.6642
+- Loss: 0.1176
+- Wer: 51.3644
 
 ## Model description
 
@@ -57,8 +57,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.6325        | 0.4   | 50   | 0.3366          | 97.8901 |
-| 0.2317        | 0.8   | 100  | 0.2549          | 98.6642 |
+| 0.1795        | 0.38  | 50   | 0.1488          | 58.9789 |
+| 0.1259        | 0.75  | 100  | 0.1176          | 51.3644 |
 
 
 ### Framework versions

runs/Feb26_15-23-40_2c89ad9839cb/events.out.tfevents.1708961022.2c89ad9839cb.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a5df210b543d51b7942d999e93b2da41efcbf73ae7d14e2eaa0c3b7d9280a0
-size 6218
+oid sha256:1fd1f39de140d930af9cb0bfc444be99fc17f25c8f1c36c1f6a9898b1ffb8201
+size 6566