EzraWilliam
/

wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

EzraWilliam commited on Sep 26, 2023

Commit

7a1e9cb

•

1 Parent(s): 8f6a71d

End of training

Files changed (1) hide show

README.md +4 -8

README.md CHANGED Viewed

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5099
-- Wer: 0.7823
 ## Model description
@@ -50,12 +50,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 4.3441        | 4.59  | 500  | 2.8658          | 1.0    |
-| 1.1862        | 9.17  | 1000 | 1.2467          | 0.8572 |
-| 0.4708        | 13.76 | 1500 | 1.3497          | 0.8065 |
-| 0.3068        | 18.35 | 2000 | 1.3890          | 0.7881 |
-| 0.2223        | 22.94 | 2500 | 1.3892          | 0.7720 |
-| 0.1808        | 27.52 | 3000 | 1.5099          | 0.7823 |
 ### Framework versions

 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.6817
+- Wer: 0.9964
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 4.9984        | 11.9  | 500  | 2.8550          | 1.0    |
+| 1.5009        | 23.81 | 1000 | 1.6817          | 0.9964 |
 ### Framework versions