End of training

README.md

@@ -17,7 +17,7 @@ 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: 0.4606
+- Loss: 0.4629
 
 ## Model description
 
@@ -37,11 +37,9 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
+- train_batch_size: 32
 - eval_batch_size: 2
 - seed: 42
-- gradient_accumulation_steps: 8
-- 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
@@ -52,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5175        | 4.3   | 1000 | 0.4804          |
-| 0.4971        | 8.61  | 2000 | 0.4673          |
-| 0.4906        | 12.91 | 3000 | 0.4614          |
-| 0.4941        | 17.21 | 4000 | 0.4606          |
+| 0.5217        | 4.29  | 1000 | 0.4829          |
+| 0.5005        | 8.58  | 2000 | 0.4697          |
+| 0.4887        | 12.88 | 3000 | 0.4633          |
+| 0.496         | 17.17 | 4000 | 0.4629          |
 
 
 ### Framework versions