|
--- |
|
language: |
|
- vi |
|
tags: |
|
- text-to-speech |
|
- vivos |
|
datasets: |
|
- vivos |
|
model-index: |
|
- name: SpeechT5 TTS Vietnamese |
|
results: [] |
|
pipeline-tag: |
|
- text-to-speech |
|
widget: |
|
- text: "Đây được xem là truyện thơ nổi tiếng nhất và xét vào hàng kinh điển trong văn học Việt Nam." |
|
--- |
|
|
|
<!-- 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 Vietnamese |
|
|
|
This model is a fine-tuned version of [speechT5](https://huggingface.co/docs/transformers/main/en/model_doc/speecht5) on the [vivos](https://huggingface.co/vivos) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4314 |
|
|
|
## 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 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.4969 | 2.81 | 1000 | 0.4549 | |
|
| 0.4933 | 5.63 | 2000 | 0.4433 | |
|
| 0.4713 | 8.44 | 3000 | 0.4316 | |
|
| 0.4733 | 11.25 | 4000 | 0.4314 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.0.dev0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
