metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_zaldyseno_id_v2
results: []
speecht5_finetuned_zaldyseno_id_v2
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: 0.5170
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 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: 100
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.711 | 0.2495 | 100 | 0.6076 |
| 0.6511 | 0.4989 | 200 | 0.5754 |
| 0.6005 | 0.7484 | 300 | 0.5506 |
| 0.5932 | 0.9978 | 400 | 0.5343 |
| 0.5711 | 1.2470 | 500 | 0.5241 |
| 0.5585 | 1.4964 | 600 | 0.5170 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1