SuperKogito
/

whisper-base-nl-2

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

SuperKogito commited on Jan 16, 2023

Commit

ec5d524

•

1 Parent(s): 8c28920

update model card README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5007
-- Wer: 25.2933
-- Cer: 8.5757
 ## Model description
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer     | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
-| 0.3749        | 0.14  | 1000 | 0.5007          | 25.2933 | 8.5757 |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4946
+- Wer: 25.6740
+- Cer: 8.4872
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer     | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
+| 0.4709        | 0.12  | 1000 | 0.4946          | 25.6740 | 8.4872 |
 ### Framework versions