metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- keithito/lj_speech
model-index:
- name: speecht5_finetuned_lj_speech
results: []
pipeline_tag: text-to-speech
speecht5_finetuned_lj_speech
This model is a fine-tuned version of microsoft/speecht5_tts on the keithito/lj_speech dataset. It achieves the following results on the evaluation set:
- Loss: 0.3772
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: 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4519 | 1.3569 | 500 | 0.4035 |
| 0.4307 | 2.7137 | 1000 | 0.3897 |
| 0.4243 | 4.0706 | 1500 | 0.3842 |
| 0.4154 | 5.4274 | 2000 | 0.3814 |
| 0.4158 | 6.7843 | 2500 | 0.3793 |
| 0.409 | 8.1411 | 3000 | 0.3783 |
| 0.4112 | 9.4980 | 3500 | 0.3774 |
| 0.4135 | 10.8548 | 4000 | 0.3772 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0