End of training

README.md

@@ -17,7 +17,7 @@ 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 the voxpopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4588
+- Loss: 0.4626
 
 ## Model description
 
@@ -38,7 +38,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 4
-- eval_batch_size: 4
+- eval_batch_size: 2
 - seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 32
@@ -52,10 +52,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 0.5165        | 4.3034  | 1000 | 0.4787          |
-| 0.4958        | 8.6068  | 2000 | 0.4645          |
-| 0.4903        | 12.9102 | 3000 | 0.4591          |
-| 0.4914        | 17.2136 | 4000 | 0.4588          |
+| 0.5168        | 4.3034  | 1000 | 0.4836          |
+| 0.4941        | 8.6068  | 2000 | 0.4683          |
+| 0.4914        | 12.9102 | 3000 | 0.4647          |
+| 0.4919        | 17.2136 | 4000 | 0.4626          |
 
 
 ### Framework versions