|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: microsoft/speecht5_tts |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: speecht5_mal |
|
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_mal |
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6822 |
|
|
|
## 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: Use 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: 10 |
|
- training_steps: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.914 | 0.0931 | 10 | 0.8044 | |
|
| 0.8931 | 0.1863 | 20 | 0.7753 | |
|
| 0.8891 | 0.2794 | 30 | 0.7568 | |
|
| 0.8441 | 0.3725 | 40 | 0.7429 | |
|
| 0.8272 | 0.4657 | 50 | 0.7300 | |
|
| 0.8317 | 0.5588 | 60 | 0.7215 | |
|
| 0.8057 | 0.6519 | 70 | 0.7062 | |
|
| 0.8071 | 0.7451 | 80 | 0.6954 | |
|
| 0.7727 | 0.8382 | 90 | 0.6825 | |
|
| 0.7823 | 0.9313 | 100 | 0.6822 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.0 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.3.1 |
|
- Tokenizers 0.21.0 |
|
|
