metadata
language:
- it
license: mit
tags:
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: SpeechT5-it
results: []
SpeechT5-it
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: 0.4900
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: 8
- 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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5788 | 1.0 | 356 | 0.5208 |
| 0.5538 | 2.0 | 712 | 0.5011 |
| 0.5453 | 3.0 | 1068 | 0.4948 |
| 0.5382 | 4.0 | 1424 | 0.4940 |
| 0.5315 | 5.0 | 1780 | 0.4900 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3