End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 61.53662039253231
+      value: 64.48061273336525
 ---
 
 <!-- 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: 0.5874
-- Wer: 61.5366
+- Loss: 0.5847
+- Wer: 64.4806
 
 ## Model description
 
@@ -68,16 +68,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 2.3992        | 0.9524 | 100  | 0.9485          | 85.2082 |
-| 0.6313        | 1.9048 | 200  | 0.6889          | 72.1876 |
-| 0.3732        | 2.8571 | 300  | 0.6084          | 63.9301 |
-| 0.2356        | 3.8095 | 400  | 0.5848          | 66.1321 |
-| 0.1439        | 4.7619 | 500  | 0.5874          | 61.5366 |
+| 2.4447        | 0.7692 | 100  | 0.9750          | 88.2001 |
+| 0.6471        | 1.5385 | 200  | 0.7163          | 74.5811 |
+| 0.3822        | 2.3077 | 300  | 0.6274          | 66.7066 |
+| 0.2487        | 3.0769 | 400  | 0.6025          | 66.4911 |
+| 0.1549        | 3.8462 | 500  | 0.5847          | 64.4806 |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
+- Transformers 4.44.0
 - Pytorch 2.3.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

generation_config.json

@@ -252,5 +252,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.42.4"
+  "transformers_version": "4.44.0"
 }