scasutt
/

Prototype_training

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions

scasutt commited on Dec 28, 2021

Commit

57c522b

·

1 Parent(s): d5eb017

update model card README.md

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [scasutt/Prototype_training](https://huggingface.co/scasutt/Prototype_training) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6499
-- Wer: 0.6750
 ## Model description
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.5865        | 0.74  | 100  | 0.6499          | 0.6750 |
-| 0.5801        | 1.47  | 200  | 0.6499          | 0.6750 |
-| 0.5808        | 2.21  | 300  | 0.6499          | 0.6750 |
-| 0.5734        | 2.94  | 400  | 0.6499          | 0.6750 |
-| 0.5706        | 3.68  | 500  | 0.6499          | 0.6750 |
 ### Framework versions

 This model is a fine-tuned version of [scasutt/Prototype_training](https://huggingface.co/scasutt/Prototype_training) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.6686
+- Wer: 0.6639
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.6613        | 0.74  | 100  | 0.6388          | 0.6609 |
+| 0.5528        | 1.47  | 200  | 0.6396          | 0.6569 |
+| 0.5148        | 2.21  | 300  | 0.6362          | 0.6681 |
+| 0.4727        | 2.94  | 400  | 0.6537          | 0.6711 |
+| 0.4415        | 3.68  | 500  | 0.6686          | 0.6639 |
 ### Framework versions