|
--- |
|
language: |
|
- sl |
|
base_model: SpeechT5ForTextToSpeech |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- facebook/voxpopuli |
|
model-index: |
|
- name: TTS Model Slovene - Yang |
|
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. --> |
|
|
|
# TTS Model Slovene - Yang |
|
|
|
This model is a fine-tuned version of [SpeechT5ForTextToSpeech](https://huggingface.co/SpeechT5ForTextToSpeech) on the VoxPopuli Slovene dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5173 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- 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: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.463 | 63.49 | 1000 | 0.5187 | |
|
| 0.4513 | 126.98 | 2000 | 0.5173 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
