End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 72.71421732886549
+      value: 69.88989947343227
 ---
 
 <!-- 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 [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 16 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6278
-- Wer: 72.7142
+- Loss: 0.6415
+- Wer: 69.8899
 
 ## Model description
 
@@ -68,16 +68,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 2.6628        | 0.0573 | 100  | 1.1337          | 94.6146 |
-| 1.1593        | 0.1147 | 200  | 0.8508          | 75.5385 |
-| 0.9433        | 0.1720 | 300  | 0.7360          | 71.7808 |
-| 0.8171        | 0.2294 | 400  | 0.6978          | 66.9459 |
-| 0.7444        | 0.2867 | 500  | 0.6278          | 72.7142 |
+| 3.1343        | 0.0991 | 100  | 1.2011          | 95.8353 |
+| 1.3756        | 0.1982 | 200  | 0.8742          | 80.2776 |
+| 1.14          | 0.2973 | 300  | 0.7722          | 73.4323 |
+| 0.9782        | 0.3964 | 400  | 0.6797          | 70.0096 |
+| 0.8545        | 0.4955 | 500  | 0.6415          | 69.8899 |
 
 
 ### Framework versions
 
 - Transformers 4.44.0
 - Pytorch 2.3.1+cu121
-- Datasets 2.20.0
+- Datasets 2.21.0
 - Tokenizers 0.19.1