---
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: speecht5-tts-finetuned-es
  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-finetuned-es

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: 0.4492

## 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: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.499         | 1.67  | 1000 | 0.4683          |
| 0.4826        | 3.33  | 2000 | 0.4572          |
| 0.4743        | 5.0   | 3000 | 0.4520          |
| 0.4678        | 6.67  | 4000 | 0.4499          |
| 0.4665        | 8.33  | 5000 | 0.4492          |


### Framework versions

- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2