|
---
|
|
library_name: transformers
|
|
language:
|
|
- es
|
|
license: mit
|
|
base_model: microsoft/speecht5_tts
|
|
tags:
|
|
- speech-synthesis
|
|
- tts
|
|
- spanish
|
|
- generated_from_trainer
|
|
datasets:
|
|
- mozilla-foundation/common_voice_13_0
|
|
model-index:
|
|
- name: SpeechT5 TTS Espanol
|
|
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 Espanol
|
|
|
|
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: 0.4665
|
|
|
|
## 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 |
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
| 0.5511 | 1.0941 | 1000 | 0.4901 |
|
|
| 0.515 | 2.1883 | 2000 | 0.4760 |
|
|
| 0.5032 | 3.2824 | 3000 | 0.4707 |
|
|
| 0.5076 | 4.3766 | 4000 | 0.4665 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.47.0.dev0
|
|
- Pytorch 2.5.1+cu121
|
|
- Datasets 3.1.0
|
|
- Tokenizers 0.20.1
|
|
|
