End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3333
+- Loss: 0.3382
 
 ## Model description
 
@@ -50,19 +50,19 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.4089        | 0.4188 | 500  | 0.3876          |
-| 0.4046        | 0.8377 | 1000 | 0.3756          |
-| 0.4013        | 1.2565 | 1500 | 0.3666          |
-| 0.396         | 1.6754 | 2000 | 0.3648          |
-| 0.3829        | 2.0942 | 2500 | 0.3528          |
-| 0.3786        | 2.5131 | 3000 | 0.3410          |
-| 0.3663        | 2.9319 | 3500 | 0.3374          |
-| 0.359         | 3.3508 | 4000 | 0.3333          |
+| 0.5277        | 0.4188 | 500  | 0.4806          |
+| 0.4582        | 0.8377 | 1000 | 0.4116          |
+| 0.4312        | 1.2565 | 1500 | 0.3951          |
+| 0.4122        | 1.6754 | 2000 | 0.3768          |
+| 0.3985        | 2.0942 | 2500 | 0.3599          |
+| 0.3873        | 2.5131 | 3000 | 0.3478          |
+| 0.376         | 2.9319 | 3500 | 0.3422          |
+| 0.367         | 3.3508 | 4000 | 0.3382          |
 
 
 ### Framework versions
 
 - Transformers 4.41.0.dev0
 - Pytorch 2.2.1+cu121
-- Datasets 2.19.0
+- Datasets 2.19.1
 - Tokenizers 0.19.1