metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned
results: []
speecht5_finetuned
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: 0.4463
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 |
|---|---|---|---|
| 0.579 | 0.3168 | 100 | 0.5113 |
| 0.5433 | 0.6337 | 200 | 0.4886 |
| 0.5297 | 0.9505 | 300 | 0.4751 |
| 0.5082 | 1.2673 | 400 | 0.4671 |
| 0.4985 | 1.5842 | 500 | 0.4610 |
| 0.5006 | 1.9010 | 600 | 0.4590 |
| 0.4908 | 2.2178 | 700 | 0.4533 |
| 0.4877 | 2.5347 | 800 | 0.4542 |
| 0.4861 | 2.8515 | 900 | 0.4481 |
| 0.4745 | 3.1683 | 1000 | 0.4463 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1