metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: zlm_b32_le4_s8000
results: []
zlm_b32_le4_s8000
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: 0.3161
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: 2
- 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: 2000
- training_steps: 8000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3712 | 0.2094 | 500 | 0.3402 |
| 0.3792 | 0.4188 | 1000 | 0.3468 |
| 0.374 | 0.6283 | 1500 | 0.3445 |
| 0.3701 | 0.8377 | 2000 | 0.3469 |
| 0.3828 | 1.0471 | 2500 | 0.3560 |
| 0.3697 | 1.2565 | 3000 | 0.3404 |
| 0.3719 | 1.4660 | 3500 | 0.3373 |
| 0.3682 | 1.6754 | 4000 | 0.3358 |
| 0.365 | 1.8848 | 4500 | 0.3351 |
| 0.3759 | 2.0942 | 5000 | 0.3276 |
| 0.3628 | 2.3037 | 5500 | 0.3276 |
| 0.3584 | 2.5131 | 6000 | 0.3218 |
| 0.3543 | 2.7225 | 6500 | 0.3218 |
| 0.3512 | 2.9319 | 7000 | 0.3184 |
| 0.3397 | 3.1414 | 7500 | 0.3170 |
| 0.3392 | 3.3508 | 8000 | 0.3161 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1