update model card README.md

README.md

@@ -14,9 +14,9 @@ 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, urdu dataset.
+This model is a fine-tuned version of [arham061/speecht5_finetuned_voxpopuli_nl](https://huggingface.co/arham061/speecht5_finetuned_voxpopuli_nl) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4856
+- Loss: 0.5508
 
 ## Model description
 
@@ -44,16 +44,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- training_steps: 3000
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.559         | 8.61  | 1000 | 0.5048          |
-| 0.5196        | 17.22 | 2000 | 0.4883          |
-| 0.508         | 25.83 | 3000 | 0.4859          |
-| 0.5042        | 34.45 | 4000 | 0.4856          |
+| 0.5058        | 7.74  | 1000 | 0.5431          |
+| 0.4938        | 15.49 | 2000 | 0.5487          |
+| 0.4909        | 23.23 | 3000 | 0.5508          |
 
 
 ### Framework versions