metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
- audio
- text-to-speech
datasets:
- voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_lt
results: []
pipeline_tag: text-to-speech
language:
- lt
speecht5_finetuned_voxpopuli_lt
This model is a fine-tuned version of microsoft/speecht5_tts on the voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.5631
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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4674 | 444.44 | 1000 | 0.5797 |
| 0.4314 | 888.89 | 2000 | 0.5502 |
| 0.4122 | 1333.33 | 3000 | 0.5617 |
| 0.4055 | 1777.78 | 4000 | 0.5631 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3