update model card README.md

README.md

@@ -19,7 +19,12 @@ 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 Commonvoice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5622
+- eval_loss: 0.5261
+- eval_runtime: 45.091
+- eval_samples_per_second: 22.177
+- eval_steps_per_second: 1.397
+- epoch: 8.02
+- step: 4000
 
 ## Model description
 
@@ -39,25 +44,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- total_train_batch_size: 32
 - 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 results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.6424        | 1.01  | 1000 | 0.6046          |
-| 0.6062        | 2.02  | 2000 | 0.5776          |
-| 0.5835        | 3.03  | 3000 | 0.5676          |
-| 0.5826        | 4.04  | 4000 | 0.5622          |
-
+- training_steps: 8000
 
 ### Framework versions