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-small](https://huggingface.co/openai/whisper-small) on the Common Voice 20.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6051
+- Loss: 0.7437
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.1012        | 0.7418 | 500  | 0.7840          |
-| 0.5201        | 1.4837 | 1000 | 0.6686          |
-| 0.3054        | 2.2255 | 1500 | 0.6400          |
-| 0.1285        | 2.9674 | 2000 | 0.6051          |
+| 0.2314        | 0.7418 | 500  | 0.8094          |
+| 0.1647        | 1.4837 | 1000 | 0.7804          |
+| 0.0946        | 2.2255 | 1500 | 0.7939          |
+| 0.0309        | 2.9674 | 2000 | 0.7437          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c72f79f09b181ad21fbe2c1434c032376dc083f0beb9663b08cc2441bb98a5
+oid sha256:e0b8e8eb4ef66a77252bdb11f79e1283058141825c38ed47ebb1730899d20a9d
 size 966995080