---
language:
- sv
license: mit
tags:
- common_voice
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
model-index:
- name: SpeechT5 TTS Swedish
  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 Swedish

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Common Voice dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4600

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5448        | 4.48  | 1000 | 0.4949          |
| 0.5233        | 8.97  | 2000 | 0.4699          |
| 0.4976        | 13.45 | 3000 | 0.4652          |
| 0.4943        | 17.94 | 4000 | 0.4600          |


### Framework versions

- Transformers 4.30.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.13.3