End of training

README.md

@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4837
-- Wer: 76.8908
+- Loss: 1.1623
+- Wer: 87.6048
 
 ## Model description
 
@@ -56,8 +56,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.5405        | 1.0   | 1    | 1.6214          | 94.9580 |
-| 0.5417        | 2.0   | 2    | 1.4837          | 76.8908 |
+| 1.5395        | 0.04  | 1    | 1.3495          | 82.6772 |
+| 1.6679        | 0.08  | 2    | 1.1623          | 87.6048 |
 
 
 ### Framework versions

runs/Nov10_07-06-58_1c1949debbb2/events.out.tfevents.1699600054.1c1949debbb2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c618f049c23cc011d74ba28bf737c8575689c6a74238d88fc77f1db61b661830
-size 5646
+oid sha256:9449ba6e1f525059f64cb53f401dfc435762c43a16676cbe2cca441dbcc9b767
+size 6306