update model card README.md

README.md

@@ -2,8 +2,6 @@
 license: mit
 tags:
 - generated_from_trainer
-datasets:
-- common_voice_13_0
 model-index:
 - name: speecht5_finetuned_voxpopuli_nl
   results: []
@@ -14,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_voxpopuli_nl
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_13_0 dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4795
+- Loss: 0.4881
 
 ## Model description
 
@@ -50,10 +48,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5544        | 8.61  | 1000 | 0.5004          |
-| 0.5229        | 17.22 | 2000 | 0.4859          |
-| 0.5055        | 25.83 | 3000 | 0.4780          |
-| 0.5044        | 34.45 | 4000 | 0.4795          |
+| 0.5694        | 3.73  | 1000 | 0.5130          |
+| 0.5397        | 7.45  | 2000 | 0.4972          |
+| 0.5231        | 11.18 | 3000 | 0.4907          |
+| 0.5196        | 14.9  | 4000 | 0.4881          |
 
 
 ### Framework versions