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: 0.7208
-- Cer: 82.3229
+- Loss: 0.6025
+- Cer: 89.9927
 
 ## Model description
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Cer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.1733        | 1.0   | 113  | 0.7586          | 63.1848 |
-| 0.1093        | 2.0   | 226  | 0.7071          | 81.5924 |
-| 0.0467        | 3.0   | 339  | 0.7208          | 82.3229 |
+| 0.5908        | 1.0   | 113  | 0.6514          | 99.7078 |
+| 0.3197        | 2.0   | 226  | 0.6254          | 90.9423 |
+| 0.1429        | 3.0   | 339  | 0.6025          | 89.9927 |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0063ca68e637ef31b1899f793e2b031af520d0f9b603af422b8b4a4d92d81730
+oid sha256:c983e283b96ade26274cd2c0de873387028289e57f7cbec42965c43ace2ff39d
 size 62969640