cymen-arfor
/

whisper-large-v2-ca-15awr

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

wanasash commited on 17 days ago

Commit

97655eb

•

1 Parent(s): c7b909e

Model save

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-large-v2-ca-10awr
-This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the cymen-arfor/15awr train[:66%] main dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0314
-- Wer: 0.3836
 ## Model description
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch   | Step | Validation Loss | Wer    |
 |:-------------:|:-------:|:----:|:---------------:|:------:|
-| 0.1503        | 4.7281  | 1000 | 0.6544          | 0.4245 |
-| 0.018         | 9.4563  | 2000 | 0.8409          | 0.3931 |
-| 0.0041        | 14.1844 | 3000 | 0.9081          | 0.3811 |
-| 0.0006        | 18.9125 | 4000 | 1.0021          | 0.3840 |
-| 0.0005        | 23.6407 | 5000 | 1.0314          | 0.3836 |
 ### Framework versions

 # whisper-large-v2-ca-10awr
+This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.9218
+- Wer: 0.3557
 ## Model description
 | Training Loss | Epoch   | Step | Validation Loss | Wer    |
 |:-------------:|:-------:|:----:|:---------------:|:------:|
+| 0.18          | 3.1201  | 1000 | 0.5585          | 0.3771 |
+| 0.0328        | 6.2402  | 2000 | 0.6915          | 0.3700 |
+| 0.0086        | 9.3604  | 3000 | 0.8111          | 0.3621 |
+| 0.0017        | 12.4805 | 4000 | 0.8715          | 0.3603 |
+| 0.0008        | 15.6006 | 5000 | 0.9218          | 0.3557 |
 ### Framework versions