metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: zlm_b128_le4_s4000
results: []
zlm_b128_le4_s4000
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: 0.3305
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5173 | 0.8377 | 500 | 0.4566 |
| 0.455 | 1.6754 | 1000 | 0.4031 |
| 0.4175 | 2.5131 | 1500 | 0.3778 |
| 0.4022 | 3.3508 | 2000 | 0.3678 |
| 0.3848 | 4.1885 | 2500 | 0.3523 |
| 0.3763 | 5.0262 | 3000 | 0.3426 |
| 0.3665 | 5.8639 | 3500 | 0.3398 |
| 0.3642 | 6.7016 | 4000 | 0.3305 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1