jongilnose/whisper-small-kopeak

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-small](https://huggingface.co/openai/whisper-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5076
-- Wer: 76.1329
+- Loss: 0.4960
+- Wer: 88.0161
 
 ## Model description
 
@@ -48,12 +48,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer      |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.0002        | 52.63  | 1000 | 0.4283          | 133.7362 |
-| 0.0001        | 105.26 | 2000 | 0.4713          | 90.4330  |
-| 0.0001        | 157.89 | 3000 | 0.4976          | 91.7422  |
-| 0.0           | 210.53 | 4000 | 0.5076          | 76.1329  |
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.0002        | 52.63  | 1000 | 0.4190          | 84.7936 |
+| 0.0001        | 105.26 | 2000 | 0.4605          | 76.2336 |
+| 0.0001        | 157.89 | 3000 | 0.4860          | 81.4703 |
+| 0.0001        | 210.53 | 4000 | 0.4960          | 88.0161 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbfb3a636356ab841f79aa88559deae43f41b71c987dde70acafb5fbf0479b1c
+oid sha256:55f1f77f4dc86c7634c7291efe276c3778e5c62fb9faaca1a951951079cd7d8b
 size 967102729