metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: ceb_b128_le5_s4000
results: []
ceb_b128_le5_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: 0.3943
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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 |
---|---|---|---|
0.5272 | 39.2157 | 500 | 0.4584 |
0.4634 | 78.4314 | 1000 | 0.4220 |
0.4466 | 117.6471 | 1500 | 0.4104 |
0.4289 | 156.8627 | 2000 | 0.4017 |
0.4223 | 196.0784 | 2500 | 0.3969 |
0.4149 | 235.2941 | 3000 | 0.3960 |
0.4129 | 274.5098 | 3500 | 0.3962 |
0.4108 | 313.7255 | 4000 | 0.3943 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1