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: 0.2442
-- Wer: 30.6071
+- Loss: 0.2111
+- Wer: 28.4992
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.257         | 1.2698 | 40   | 0.1940          | 30.9444 |
-| 0.1177        | 2.5397 | 80   | 0.1945          | 31.1973 |
-| 0.0569        | 3.8095 | 120  | 0.2078          | 29.3423 |
-| 0.0313        | 5.0794 | 160  | 0.2350          | 31.0287 |
-| 0.0186        | 6.3492 | 200  | 0.2442          | 30.6071 |
+| 0.2574        | 1.2698 | 40   | 0.1821          | 29.8482 |
+| 0.1075        | 2.5397 | 80   | 0.1829          | 28.9207 |
+| 0.0513        | 3.8095 | 120  | 0.1852          | 28.2462 |
+| 0.0283        | 5.0794 | 160  | 0.1992          | 29.5110 |
+| 0.0178        | 6.3492 | 200  | 0.2111          | 28.4992 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fccac904c2ab09f67f4122971938bc32996243dfb780336a3f2ec9a5dc0e621
+oid sha256:6993d2eb56920db28a25a0241d646d0cc3d87980efa46bdd0408aa766dcdcb94
 size 151099494