End of training

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 20.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6866
+- Loss: 0.6906
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.1201        | 0.7418 | 500  | 0.8695          |
-| 0.6006        | 1.4837 | 1000 | 0.7426          |
-| 0.3827        | 2.2255 | 1500 | 0.7159          |
-| 0.1953        | 2.9674 | 2000 | 0.6866          |
+| 1.122         | 0.7418 | 500  | 0.8552          |
+| 0.5987        | 1.4837 | 1000 | 0.7422          |
+| 0.3821        | 2.2255 | 1500 | 0.7093          |
+| 0.1938        | 2.9674 | 2000 | 0.6906          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081b9e5effa6d4deb32943e6a2a4f58f50177e2ea80a5c8079d30d670a777941
+oid sha256:eee38c6fd1807e57ae0d63c2365ec82c10c52953291ea2b7f178e0b471e9dae0
 size 290403936