update model card README.md

README.md

@@ -14,7 +14,7 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4167
+- Loss: 0.4112
 
 ## Model description
 
@@ -42,16 +42,22 @@ 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: 10000
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.4893        | 4.06  | 1000 | 0.4403          |
-| 0.4616        | 8.12  | 2000 | 0.4212          |
-| 0.4577        | 12.18 | 3000 | 0.4175          |
-| 0.4528        | 16.24 | 4000 | 0.4167          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.4831        | 4.06  | 1000  | 0.4406          |
+| 0.4583        | 8.12  | 2000  | 0.4271          |
+| 0.4482        | 12.18 | 3000  | 0.4177          |
+| 0.4435        | 16.24 | 4000  | 0.4148          |
+| 0.433         | 20.3  | 5000  | 0.4142          |
+| 0.4333        | 24.37 | 6000  | 0.4128          |
+| 0.4306        | 28.43 | 7000  | 0.4111          |
+| 0.4288        | 32.49 | 8000  | 0.4110          |
+| 0.4262        | 36.55 | 9000  | 0.4109          |
+| 0.4228        | 40.61 | 10000 | 0.4112          |
 
 
 ### Framework versions