metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- text-to-speech
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_it
results: []
speecht5_finetuned_voxpopuli_it
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: 0.4790
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: 5e-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: 7000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5214 | 4.72 | 1000 | 0.4866 |
| 0.4964 | 9.43 | 2000 | 0.4788 |
| 0.4843 | 14.15 | 3000 | 0.4780 |
| 0.4831 | 18.87 | 4000 | 0.4754 |
| 0.4751 | 23.58 | 5000 | 0.4781 |
| 0.4692 | 28.3 | 6000 | 0.4790 |
| 0.4661 | 33.02 | 7000 | 0.4790 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3