metadata
license: mit
tags:
- generated_from_trainer
- text-to-speech
datasets:
- facebook/voxpopuli
base_model: microsoft/speecht5_tts
model-index:
- name: speecht5_tts-finetuned-voxpopuli-sk-v1
results: []
speecht5_tts-finetuned-voxpopuli-sk-v1
This model is a fine-tuned version of microsoft/speecht5_tts on the facebook/voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.4741
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: 100
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6363 | 0.52 | 100 | 0.5600 |
| 0.5576 | 1.05 | 200 | 0.4951 |
| 0.5299 | 1.57 | 300 | 0.4798 |
| 0.5284 | 2.09 | 400 | 0.4755 |
| 0.5266 | 2.62 | 500 | 0.4741 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3