End of training

README.md

@@ -31,8 +31,8 @@ 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: 0.1371
-- Wer Ortho: 0.1544
 - Wer: 0.1052
+- Wer Ortho: 0.1544
 
 ## Model description
 
@@ -77,9 +77,9 @@ The following hyperparameters were used during training:
 | 0.0012        | 10.0  | 570  | 0.8281          | 0.1957 | 0.2450    |
 | 0.0006        | 11.0  | 627  | 0.8269          | 0.1867 | 0.2362    |
 | 0.0003        | 12.0  | 684  | 0.8332          | 0.1867 | 0.2355    |
-| 0.1651        | 13.0  | 741  | 0.1350          | 0.1807 | 0.1212    |
-| 0.061         | 14.0  | 798  | 0.1365          | 0.1539 | 0.1078    |
-| 0.0353        | 15.0  | 855  | 0.1371          | 0.1544 | 0.1052    |
+| 0.1651        | 13.0  | 741  | 0.1350          | 0.1212 | 0.1807    |
+| 0.061         | 14.0  | 798  | 0.1365          | 0.1078 | 0.1539    |
+| 0.0353        | 15.0  | 855  | 0.1371          | 0.1052 | 0.1544    |
 
 
 ### Framework versions

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03855a53a909c5ccb13ce0e8bd6c7749b09aaa2714e64f51fdd42c9e9aaa0725
+oid sha256:d3f380609876da1f47294b4ae9868dfc03770390ea8ecd63a14e1fe6f7c85fe0
 size 5841