Ansu
/

whisper-tiny-basque

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3234
-- Wer: 22.3492
 ## Model description
@@ -51,26 +51,26 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss | Wer     |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|
-| 0.5125        | 0.33  | 500   | 0.6977          | 54.1027 |
-| 0.3119        | 0.66  | 1000  | 0.5082          | 37.1862 |
-| 0.2552        | 0.99  | 1500  | 0.4232          | 30.3422 |
-| 0.2102        | 1.32  | 2000  | 0.3911          | 28.6624 |
-| 0.1925        | 1.65  | 2500  | 0.3736          | 26.8952 |
-| 0.1768        | 1.98  | 3000  | 0.3587          | 24.9969 |
-| 0.1572        | 2.31  | 3500  | 0.3541          | 26.0210 |
-| 0.1503        | 2.64  | 4000  | 0.3431          | 24.2538 |
-| 0.1485        | 2.97  | 4500  | 0.3345          | 22.8925 |
-| 0.131         | 3.3   | 5000  | 0.3336          | 22.9986 |
-| 0.1294        | 3.63  | 5500  | 0.3305          | 22.7676 |
-| 0.1287        | 3.96  | 6000  | 0.3294          | 22.7364 |
-| 0.1153        | 4.29  | 6500  | 0.3269          | 22.1931 |
-| 0.1176        | 4.62  | 7000  | 0.3243          | 23.3046 |
-| 0.1153        | 4.95  | 7500  | 0.3261          | 22.6802 |
-| 0.1094        | 5.28  | 8000  | 0.3249          | 22.9174 |
-| 0.1129        | 5.61  | 8500  | 0.3244          | 23.7917 |
-| 0.107         | 5.94  | 9000  | 0.3233          | 23.1360 |
-| 0.1029        | 6.27  | 9500  | 0.3235          | 22.3867 |
-| 0.1056        | 6.61  | 10000 | 0.3234          | 22.3492 |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.3235
+- Wer: 22.3867
 ## Model description
 | Training Loss | Epoch | Step  | Validation Loss | Wer     |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|
+| 0.5126        | 0.33  | 500   | 0.6979          | 53.3533 |
+| 0.3117        | 0.66  | 1000  | 0.5084          | 37.0488 |
+| 0.2552        | 0.99  | 1500  | 0.4231          | 30.1736 |
+| 0.2102        | 1.32  | 2000  | 0.3911          | 29.4055 |
+| 0.1925        | 1.65  | 2500  | 0.3738          | 26.7079 |
+| 0.1767        | 1.98  | 3000  | 0.3588          | 24.9469 |
+| 0.1572        | 2.31  | 3500  | 0.3541          | 25.3466 |
+| 0.1503        | 2.64  | 4000  | 0.3432          | 24.1726 |
+| 0.1485        | 2.97  | 4500  | 0.3347          | 22.8987 |
+| 0.131         | 3.3   | 5000  | 0.3336          | 23.1173 |
+| 0.1294        | 3.63  | 5500  | 0.3305          | 23.2422 |
+| 0.1287        | 3.96  | 6000  | 0.3292          | 22.6240 |
+| 0.1153        | 4.29  | 6500  | 0.3270          | 22.5990 |
+| 0.1176        | 4.62  | 7000  | 0.3243          | 23.8167 |
+| 0.1153        | 4.95  | 7500  | 0.3262          | 22.7051 |
+| 0.1093        | 5.28  | 8000  | 0.3248          | 23.8479 |
+| 0.1129        | 5.61  | 8500  | 0.3244          | 23.7480 |
+| 0.107         | 5.94  | 9000  | 0.3233          | 22.4054 |
+| 0.1029        | 6.27  | 9500  | 0.3236          | 22.7801 |
+| 0.1056        | 6.61  | 10000 | 0.3235          | 22.3867 |
 ### Framework versions