UrukHan
/

wav2vec2-ru

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

Alikhan Urumov commited on Jun 21, 2022

Commit

0673734

·

1 Parent(s): e0a2ad4

update model card README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -13,8 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4159
-- Wer: 0.4014
 ## Model description
@@ -47,10 +47,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.5001        | 0.21  | 1000 | 0.4033          | 0.4018 |
-| 0.5231        | 0.42  | 2000 | 0.4083          | 0.4018 |
-| 0.5137        | 0.64  | 3000 | 0.4146          | 0.4042 |
-| 0.4973        | 0.85  | 4000 | 0.4159          | 0.4014 |
 ### Framework versions

 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5468
+- Wer: 0.4124
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.511         | 0.21  | 1000 | 0.5444          | 0.4183 |
+| 0.5021        | 0.43  | 2000 | 0.5727          | 0.4112 |
+| 0.4746        | 0.64  | 3000 | 0.5495          | 0.4116 |
+| 0.5052        | 0.85  | 4000 | 0.5468          | 0.4124 |
 ### Framework versions