ralsuwaidi's picture
update model card README.md
e1769ad
---
language:
- nl
license: mit
tags:
- tts
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: SpeechT5 TTS Dutch
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# SpeechT5 TTS Dutch
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: 0.4589
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5132 | 4.3 | 1000 | 0.4798 |
| 0.495 | 8.6 | 2000 | 0.4648 |
| 0.4895 | 12.9 | 3000 | 0.4600 |
| 0.488 | 17.2 | 4000 | 0.4589 |
### Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.3