---
library_name: transformers
license: mit
base_model: sophiayk20/speecht5_tts_voxpopuli_de
tags:
- generated_from_trainer
model-index:
- name: speecht5_tts_informal_de
  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_de

This model is a fine-tuned version of [sophiayk20/speecht5_tts_voxpopuli_de](https://huggingface.co/sophiayk20/speecht5_tts_voxpopuli_de) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3340

## 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: 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 |
|:-------------:|:-------:|:----:|:---------------:|
| 0.3922        | 3.5471  | 1000 | 0.3505          |
| 0.3714        | 7.0924  | 2000 | 0.3390          |
| 0.3696        | 10.6394 | 3000 | 0.3355          |
| 0.3619        | 14.1847 | 4000 | 0.3340          |


### Framework versions

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