metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: ABG_MODEL_EGP
results: []
ABG_MODEL_EGP
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: 0.5052
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|
| 0.6296 | 0.2540 | 100 | 0.5643 |
| 0.594 | 0.5079 | 200 | 0.5455 |
| 0.5713 | 0.7619 | 300 | 0.5376 |
| 0.5647 | 1.0159 | 400 | 0.5277 |
| 0.5532 | 1.2698 | 500 | 0.5221 |
| 0.5522 | 1.5238 | 600 | 0.5151 |
| 0.5477 | 1.7778 | 700 | 0.5119 |
| 0.5443 | 2.0317 | 800 | 0.5098 |
| 0.5407 | 2.2857 | 900 | 0.5068 |
| 0.5376 | 2.5397 | 1000 | 0.5052 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1