---
library_name: transformers
license: mit
base_model: sophiayk20/speecht5_tts_voxpopuli_es
tags:
- generated_from_trainer
model-index:
- name: speecht5_tts_informal_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_informal_es

This model is a fine-tuned version of [sophiayk20/speecht5_tts_voxpopuli_es](https://huggingface.co/sophiayk20/speecht5_tts_voxpopuli_es) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3486

## 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: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.4317        | 1.7769 | 1000 | 0.3729          |
| 0.3915        | 3.5529 | 2000 | 0.3583          |
| 0.3954        | 5.3289 | 3000 | 0.3530          |
| 0.3811        | 7.1049 | 4000 | 0.3486          |


### Framework versions

- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1