End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 47.1932299012694
+      value: 45.839210155148095
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [glob-asr/wav2vec2-large-xls-r-300m-guarani-small](https://huggingface.co/glob-asr/wav2vec2-large-xls-r-300m-guarani-small) on the Common Voice 16 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3483
-- Wer: 47.1932
+- Loss: 0.3327
+- Wer: 45.8392
 
 ## Model description
 
@@ -70,16 +70,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 1.1584        | 0.0574 | 100  | 0.3953          | 50.8886 |
-| 0.9553        | 0.1147 | 200  | 0.3771          | 48.0395 |
-| 0.8605        | 0.1721 | 300  | 0.3584          | 46.3188 |
-| 0.7905        | 0.2294 | 400  | 0.3528          | 47.7856 |
-| 0.8168        | 0.2868 | 500  | 0.3483          | 47.1932 |
+| 1.397         | 0.0991 | 100  | 0.3675          | 48.4062 |
+| 1.0613        | 0.1982 | 200  | 0.3604          | 50.5219 |
+| 1.0365        | 0.2973 | 300  | 0.3500          | 48.8575 |
+| 0.9822        | 0.3964 | 400  | 0.3454          | 47.5599 |
+| 0.9197        | 0.4955 | 500  | 0.3327          | 45.8392 |
 
 
 ### Framework versions
 
 - Transformers 4.44.0
 - Pytorch 2.3.1+cu121
-- Datasets 2.20.0
+- Datasets 2.21.0
 - Tokenizers 0.19.1