update model card README.md

README.md

@@ -2,6 +2,7 @@
 language:
 - nl
 license: mit
+base_model: microsoft/speecht5_tts
 tags:
 - generated_from_trainer
 datasets:
@@ -17,6 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 # SpeechT5 Dutch - WasuratS
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4614
 
 ## Model description
 
@@ -39,18 +42,26 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 2
 - seed: 42
-- distributed_type: multi-GPU
 - 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
 - training_steps: 4000
-- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5223        | 4.3   | 1000 | 0.4793          |
+| 0.4936        | 8.61  | 2000 | 0.4668          |
+| 0.4969        | 12.91 | 3000 | 0.4640          |
+| 0.4929        | 17.21 | 4000 | 0.4614          |
+
 
 ### Framework versions
 
-- Transformers 4.29.2
-- Pytorch 2.0.1+cu117
-- Datasets 2.12.0
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.13.1
 - Tokenizers 0.13.3