Model save

README.md

@@ -17,8 +17,8 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4088
-- Wer: 43.7605
+- Loss: 0.3560
+- Wer: 40.8094
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.3869        | 1.2698 | 40   | 0.3542          | 46.9646 |
-| 0.2215        | 2.5397 | 80   | 0.3464          | 45.2782 |
-| 0.1394        | 3.8095 | 120  | 0.3495          | 43.0017 |
-| 0.0857        | 5.0794 | 160  | 0.3752          | 41.3153 |
-| 0.0434        | 6.3492 | 200  | 0.4088          | 43.7605 |
+| 0.3384        | 1.2698 | 40   | 0.3002          | 39.6290 |
+| 0.1811        | 2.5397 | 80   | 0.2908          | 37.7740 |
+| 0.0989        | 3.8095 | 120  | 0.3249          | 39.7976 |
+| 0.0623        | 5.0794 | 160  | 0.3358          | 45.3626 |
+| 0.0344        | 6.3492 | 200  | 0.3560          | 40.8094 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5e7753684af5f8816490668b2f76c063c60e9d1585f52f769b551e695790a3
+oid sha256:28d00ca3bfb780e4dc72d46545fa78a6ba7b4ff64ff7fca8ceca22f284d3373c
 size 151099494