UrukHan
/

wav2vec2-ru

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Alikhan Urumov commited on Jun 21, 2022

Commit

5811e12

•

1 Parent(s): 3d38ef2

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: 0.5091
-- Wer: 0.4207
 ## Model description
@@ -47,10 +47,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.5066        | 0.21  | 1000 | 0.5071          | 0.4255 |
-| 0.4924        | 0.43  | 2000 | 0.4987          | 0.4243 |
-| 0.4861        | 0.64  | 3000 | 0.5032          | 0.4215 |
-| 0.495         | 0.85  | 4000 | 0.5091          | 0.4207 |
 ### Framework versions

 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4317
+- Wer: 0.3873
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.4959        | 0.21  | 1000 | 0.4164          | 0.3845 |
+| 0.5124        | 0.42  | 2000 | 0.4403          | 0.3889 |
+| 0.5074        | 0.64  | 3000 | 0.4324          | 0.3893 |
+| 0.5248        | 0.85  | 4000 | 0.4317          | 0.3873 |
 ### Framework versions