End of training

README.md

@@ -3,8 +3,6 @@ license: mit
 base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
-datasets:
-- voxpopuli
 model-index:
 - name: dutch_example
   results: []
@@ -15,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # dutch_example
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4629
+- Loss: 0.4487
 
 ## Model description
 
@@ -37,9 +35,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 32
+- train_batch_size: 16
 - eval_batch_size: 2
 - seed: 42
+- gradient_accumulation_steps: 2
+- 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
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 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          |
+| 0.507         | 3.13  | 1000 | 0.4653          |
+| 0.4916        | 6.26  | 2000 | 0.4531          |
+| 0.4876        | 9.39  | 3000 | 0.4488          |
+| 0.4806        | 12.52 | 4000 | 0.4487          |
 
 
 ### Framework versions