metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_uz_customDat_3
results: []
speecht5_finetuned_uz_customDat_3
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: 0.5390
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5014 | 11.7879 | 200 | 0.4656 |
| 0.4407 | 23.5455 | 400 | 0.4460 |
| 0.418 | 35.3030 | 600 | 0.4447 |
| 0.3972 | 47.0606 | 800 | 0.4652 |
| 0.3819 | 58.8485 | 1000 | 0.4874 |
| 0.373 | 70.6061 | 1200 | 0.4850 |
| 0.3709 | 82.3636 | 1400 | 0.5019 |
| 0.3631 | 94.1212 | 1600 | 0.5121 |
| 0.3595 | 105.9091 | 1800 | 0.5319 |
| 0.3647 | 117.6667 | 2000 | 0.5390 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3