End of training

README.md

@@ -2,10 +2,11 @@
 license: mit
 base_model: microsoft/speecht5_tts
 tags:
-- generated_from_trainer
 - text-to-speech
+- Dutch
+- generated_from_trainer
 datasets:
-- voxpopuli
+- facebook/voxpopuli
 model-index:
 - name: speecht5_finetuned_voxpopuli_nl
   results: []
@@ -18,7 +19,7 @@ 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: 0.4635
+- Loss: 0.4641
 
 ## Model description
 
@@ -50,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.526         | 2.15  | 1000 | 0.4841          |
-| 0.5065        | 4.3   | 2000 | 0.4707          |
-| 0.4988        | 6.45  | 3000 | 0.4652          |
-| 0.5016        | 8.6   | 4000 | 0.4635          |
+| 0.5214        | 2.15  | 1000 | 0.4842          |
+| 0.5094        | 4.3   | 2000 | 0.4713          |
+| 0.4973        | 6.45  | 3000 | 0.4649          |
+| 0.5031        | 8.6   | 4000 | 0.4641          |
 
 
 ### Framework versions
@@ -61,4 +62,4 @@ The following hyperparameters were used during training:
 - Transformers 4.32.0.dev0
 - Pytorch 2.0.1
 - Datasets 2.14.4
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3