metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- lj_speech
model-index:
- name: TTS-T5_finetuned
results: []
TTS-T5_finetuned
This model is a fine-tuned version of microsoft/speecht5_tts on the lj_speech dataset. It achieves the following results on the evaluation set:
- Loss: 0.3737
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.4677 | 0.6029 | 100 | 0.4110 |
0.4311 | 1.2102 | 200 | 0.3935 |
0.4264 | 1.8131 | 300 | 0.3827 |
0.4171 | 2.4205 | 400 | 0.3771 |
0.4132 | 3.0279 | 500 | 0.3737 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3