metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_marar1000
results: []
speecht5_finetuned_marar1000
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4988
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: 0.0001
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7169 | 3.1873 | 100 | 0.6299 |
| 0.5985 | 6.3745 | 200 | 0.5623 |
| 0.5607 | 9.5618 | 300 | 0.5406 |
| 0.5473 | 12.7490 | 400 | 0.5500 |
| 0.5191 | 15.9363 | 500 | 0.5234 |
| 0.5276 | 19.1235 | 600 | 0.5260 |
| 0.5116 | 22.3108 | 700 | 0.5064 |
| 0.504 | 25.4980 | 800 | 0.5191 |
| 0.4838 | 28.6853 | 900 | 0.5001 |
| 0.4825 | 31.8725 | 1000 | 0.4988 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Tokenizers 0.20.3