---
language:
- hr
license: mit
base_model: microsoft/speecht5_tts
tags:
- hrvatski
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: SpeechT5 TTS Croatian
  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 Croatian

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: 0.4518

## 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 |
|:-------------:|:--------:|:----:|:---------------:|
| 0.4845        | 32.2581  | 1000 | 0.4559          |
| 0.4608        | 64.5161  | 2000 | 0.4489          |
| 0.4499        | 96.7742  | 3000 | 0.4497          |
| 0.4433        | 129.0323 | 4000 | 0.4518          |


### Framework versions

- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1