---
language:
- nl
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- text-to-speech
model-index:
- name: fine-tuned-SpeechT5
  results: []
pipeline_tag: text-to-speech
---

<!-- 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. -->

# fine-tuned-SpeechT5

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: 0.4629

## 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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5223        | 3.75  | 500  | 0.4833          |
| 0.501         | 7.5   | 1000 | 0.4702          |
| 0.4909        | 11.25 | 1500 | 0.4648          |
| 0.4796        | 15.0  | 2000 | 0.4629          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2