metadata
language:
- en
license: mit
tags:
- generated_from_trainer
datasets:
- speecht5_finetuned_single_speaker_en_test_librivox
model-index:
- name: SpeechT5 Single Speaker test
results: []
SpeechT5 Single Speaker test
This model is a fine-tuned version of microsoft/speecht5_tts on the single_speaker_en_test_librivox dataset. It achieves the following results on the evaluation set:
- Loss: 0.5817
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.8228 | 0.59 | 1000 | 0.7680 |
0.74 | 1.19 | 2000 | 0.6693 |
0.6854 | 1.78 | 3000 | 0.6155 |
0.6794 | 2.37 | 4000 | 0.5908 |
0.658 | 2.97 | 5000 | 0.5817 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3