rossevine
/

Model_G_S_Berita_Wav2Vec2

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

rossevine commited on Aug 31, 2023

Commit

0c1ac1d

•

1 Parent(s): 0ac652e

update model card README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -15,9 +15,9 @@ 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: 0.0239
-- Wer: 0.0350
-- Cer: 0.0055
 ## Model description
@@ -51,13 +51,13 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 0.3535        | 12.5  | 400  | 0.0680          | 0.0888 | 0.0139 |
-| 0.0269        | 25.0  | 800  | 0.0239          | 0.0350 | 0.0055 |
 ### Framework versions
 - Transformers 4.31.0
 - Pytorch 2.0.1+cu117
-- Datasets 1.18.3
 - Tokenizers 0.13.3

 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0232
+- Wer: 0.0308
+- Cer: 0.0050
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
+| 0.3802        | 12.5  | 400  | 0.0473          | 0.0692 | 0.0105 |
+| 0.0245        | 25.0  | 800  | 0.0232          | 0.0308 | 0.0050 |
 ### Framework versions
 - Transformers 4.31.0
 - Pytorch 2.0.1+cu117
+- Datasets 2.14.4
 - Tokenizers 0.13.3