---
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- arrow
model-index:
- name: speecht5_sw_normal
  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_sw_normal

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the arrow dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5708

## 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: 2
- seed: 42
- 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: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.7131        | 2.003 | 500  | 0.6449          |
| 0.6108        | 4.006 | 1000 | 0.6056          |
| 0.6025        | 6.009 | 1500 | 0.5798          |
| 0.6159        | 8.012 | 2000 | 0.5708          |


### Framework versions

- Transformers 4.50.2
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1