240624-wav2vec2-ASR-English

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [zainulhakim/240615-wav2vec2-ASR-English](https://huggingface.co/zainulhakim/240615-wav2vec2-ASR-English) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8845
-- Wer: 0.5974
+- Loss: 0.9959
+- Wer: 0.6623
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 5.0   | 100  | 2.6315          | 1.0    |
-| No log        | 10.0  | 200  | 0.8627          | 0.8961 |
-| No log        | 15.0  | 300  | 0.8228          | 0.6494 |
-| No log        | 20.0  | 400  | 0.8845          | 0.5974 |
+| No log        | 5.0   | 100  | 2.6284          | 1.0    |
+| No log        | 10.0  | 200  | 0.8606          | 0.8831 |
+| No log        | 15.0  | 300  | 0.9080          | 0.7273 |
+| No log        | 20.0  | 400  | 0.9959          | 0.6623 |
 
 
 ### Framework versions